Intel Core Ultra 7 255H / 9 285H NAS (32 GB) spec sheet
What the Intel Core Ultra 7 255H / 9 285H NAS (32 GB) can run
We check your GPU or device against every model. Browsers can’t see how much memory you have, so confirm your exact model below.
- Unified memory
- 32.0 GB
- Usable for models
- 18.2 GB
- Memory bandwidth
- 102 GB/s
- FP16 compute
- 9.2 TFLOPS
Open in Model Finder Best LLMs by task Compare with another GPU
LLMs on the Intel Core Ultra 7 255H / 9 285H NAS (32 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 26B-A4B | Q4_K_M | 18.2 GB | 29.0 tok/s | Runs welltight fit |
| 73Great quality (A) · 73 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4.7 Flash (30B-A3B) | Q3_K_M | 17.8 GB | 45.0 tok/s | Runs welltight fit |
| 71Great quality (A) · 71 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | Hunyuan Hy-Memory 30B-A3B | Q3_K_M | 17.6 GB | 45.0 tok/s | Runs welltight fit |
| 73Great quality (A) · 73 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | Raon-1 mini Preview (30B-A4B) | Q3_K_M | 16.2 GB | 32.8 tok/s | Runs welltight fit |
| 70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | LFM2.5 24B-A2B | Q4_K_M | 16.8 GB | 42.7 tok/s | Runs welltight fit |
| 70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | gpt-oss 20B | MXFP4 | 14.2 GB | 32.4 tok/s | Runs great |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Maple Preview (20B-A1B) | Q4_K_M | 14.5 GB | 64.3 tok/s | Runs great |
| 74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | DiffusionGemma 26B-A4B IT | Q4_K_M | 18.2 GB | 27.7 tok/s | Runs welltight fit |
| 67Good quality (B) · 67 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | North Mini Code 1.0 (30B-A3B) | Q3_K_M | 17.3 GB | 45.0 tok/s | Runs welltight fit |
| 67Good quality (B) · 67 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron Cascade 2 30B-A3B | Q3_K_M | 17.6 GB | 39.4 tok/s | Runs welltight fit |
| 65Good quality (B) · 65 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 30B-A3B Thinking 2507 | Q3_K_M | 17.8 GB | 41.4 tok/s | Runs welltight fit |
| 65Good quality (B) · 65 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Coder 30B-A3B | Q3_K_M | 17.8 GB | 41.4 tok/s | Runs welltight fit |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.6 35B-A3B | Q2_K | 16.6 GB | 55.3 tok/s | Runs welltight fit |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-V 4.7 35B-A3B | Q2_K | 16.3 GB | 55.3 tok/s | Runs welltight fit |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 35B-A3B | Q2_K | 16.6 GB | 55.3 tok/s | Runs welltight fit |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE 4.5 21B-A3B Thinking | Q4_K_M | 15.8 GB | 35.8 tok/s | Runs welltight fit |
| 64Good quality (B) · 64 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 30B-A3B Instruct 2507 | Q3_K_M | 17.8 GB | 41.4 tok/s | Runs welltight fit |
| 64Good quality (B) · 64 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3 Nano 30B-A3B | Q3_K_M | 17.6 GB | 39.4 tok/s | Runs welltight fit |
| 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Nex N2 Mini (35B-A3B) | Q2_K | 16.3 GB | 55.3 tok/s | Runs welltight fit |
| 63Good quality (B) · 63 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-VL 30B-A3B Thinking | Q3_K_M | 18.1 GB | 41.4 tok/s | Runs welltight fit |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | KAT-Coder V2.5 Dev (35B-A3B) | Q2_K | 16.1 GB | 55.3 tok/s | Runs welltight fit |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Sage-A1.5 35B-A3B | Q2_K | 16.6 GB | 55.3 tok/s | Runs welltight fit |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Flint (40B-A2.5B) | Q2_K | 18.2 GB | 64.2 tok/s | Runs welltight fit |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.5 35B-A3B | Q2_K | 16.6 GB | 55.3 tok/s | Runs welltight fit |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Mellum2.1 Thinking (12B-A2.5B) | Q4_K_M | 9.6 GB | 42.0 tok/s | Runs great |
| 62Good quality (B) · 62 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Apodex 1.1 Mini (35B-A3B) | Q2_K | 16.6 GB | 55.3 tok/s | Runs welltight fit |
| 62Good quality (B) · 62 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.0 35B-A3B | Q2_K | 16.6 GB | 55.3 tok/s | Runs welltight fit |
| 62Good quality (B) · 62 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 30B-A3B | Q3_K_M | 17.8 GB | 41.4 tok/s | Runs welltight fit |
| 62Good quality (B) · 62 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-VL 30B-A3B Instruct | Q3_K_M | 18.1 GB | 41.4 tok/s | Runs welltight fit |
| 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Trinity Mini (26B-A3B) | Q4_K_M | 18.2 GB | 35.8 tok/s | Runs welltight fit |
| 60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Agents-A1 35B-A3B | Q2_K | 16.3 GB | 55.3 tok/s | Runs welltight fit |
| 60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Qwen AgentWorld 35B-A3B | Q2_K | 16.1 GB | 55.3 tok/s | Runs welltight fit |
| 60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3.5 Lightning 30B-A3B | Q3_K_M | 17.6 GB | 45.0 tok/s | Runs welltight fit |
| 80Great quality (A) · 80 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.8 27B | Q3_K_M | 16.2 GB | 5.7 tok/s | Slowtight fit |
| 78Great quality (A) · 78 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 12B | Q4_K_M | 10.0 GB | 10.2 tok/s | Runs well |
| 60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE 4.5 21B-A3B | Q4_K_M | 15.9 GB | 35.8 tok/s | Runs welltight fit |
| 60Good quality (B) · 60 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Ling 3.0 Tiny (8B-A1.3B) | Q8_0 | 10.6 GB | 40.5 tok/s | Runs great |
| 58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Sarvam 30B | Q3_K_M | 18.0 GB | 54.3 tok/s | Runs welltight fit |
| 78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.6 27B | Q3_K_M | 16.2 GB | 5.7 tok/s | Slowtight fit |
| 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Kimi-VL A3B Thinking 2506 | Q4_K_M | 12.3 GB | 35.8 tok/s | Runs great |
| 57Good quality (B) · 57 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Laguna XS 2.1 (33B-A3B) | Q2_K | 16.8 GB | 55.3 tok/s | Runs welltight fit |
| 78Great quality (A) · 78 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 27B | Q3_K_M | 16.2 GB | 5.7 tok/s | Slowtight fit |
| 77Great quality (A) · 77 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Muse Glimmer 30B | Q3_K_M | 16.8 GB | 5.3 tok/s | Slowtight fit |
| 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | K2 Horizon 7B | Q4_K_M | 8.8 GB | 13.6 tok/s | Runs well |
| 75Great quality (A) · 75 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | TMax 27B | Q3_K_M | 16.0 GB | 5.8 tok/s | Slowtight fit |
| 54Fair quality (C) · 54 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Groot 19B A3B 261023 | Q4_K_M | 14.1 GB | 35.8 tok/s | Runs great |
| 73Great quality (A) · 73 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | Fara 1.5 27B | Q3_K_M | 16.0 GB | 5.8 tok/s | Slowtight fit |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | LFM2 24B-A2B | Q4_K_M | 16.8 GB | 45.1 tok/s | Runs welltight fit |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | Ling Mini 2.0 (16B-A1.4B) | Q5_K_M | 13.9 GB | 57.6 tok/s | Runs great |
| 74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | SenseNova Loop 9B Preview | Q4_K_M | 8.4 GB | 12.7 tok/s | Runs well |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek Coder V2 Lite (16B) | Q4_K_M | 11.9 GB | 43.5 tok/s | Runs great |
| 72Great quality (A) · 72 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | UI-Mate 27B | Q3_K_M | 16.0 GB | 5.8 tok/s | Slowtight fit |
| 74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | MiMo V2.6 Distill Qwen 9B | Q4_K_M | 8.1 GB | 13.0 tok/s | Runs well |
| 72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Devstral Small 2 (24B) | Q4_K_M | 18.0 GB | 5.1 tok/s | Slowtight fit |
| 73Great quality (A) · 73 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.5 9B | Q4_K_M | 8.2 GB | 12.7 tok/s | Runs well |
| 72Great quality (A) · 72 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 9B | Q4_K_M | 8.2 GB | 12.7 tok/s | Runs well |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3.5 Bolt E4B | Q4_K_M | 7.1 GB | 27.2 tok/s | Runs well |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-Omni 30B-A3B Instruct | Q2_K | 17.0 GB | 51.1 tok/s | Runs welltight fit |
| 71Great quality (A) · 71 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.0 9B | Q4_K_M | 8.2 GB | 12.7 tok/s | Runs well |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | Kimi-VL A3B Instruct | Q4_K_M | 12.3 GB | 35.8 tok/s | Runs great |
| 64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 E4B | Q4_K_M | 7.1 GB | 27.2 tok/s | Runs well |
| 70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | TMax 9B | Q4_K_M | 7.8 GB | 13.7 tok/s | Runs well |
| 68Good quality (B) · 68 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | Magistral Small 1.2 (24B) | Q4_K_M | 18.0 GB | 5.1 tok/s | Slowtight fit |
| 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Nanbeige4.3 33B | Q2_K | 17.1 GB | 6.1 tok/s | Slowtight fit |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | LFM2.5 8B-A1B | Q6_K | 9.1 GB | 47.0 tok/s | Runs great |
| 64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Nanbeige4.2 3B | Q4_K_M | 6.1 GB | 29.3 tok/s | Runs well |
| 60Good quality (B) · 60 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 E2B | Q5_K_M | 5.8 GB | 43.9 tok/s | Runs great |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Devstral Small 1.1 (24B) | Q4_K_M | 17.8 GB | 5.2 tok/s | Slowtight fit |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Magistral Small 2507 | Q4_K_M | 17.8 GB | 5.2 tok/s | Slowtight fit |
| 64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.2 8B | Q4_K_M | 8.8 GB | 13.9 tok/s | Runs well |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Moonlight 16B-A3B Instruct | Q4_K_M | 12.0 GB | 35.8 tok/s | Runs great |
| 60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Phi-4 Reasoning Plus (14B) | Q3_K_M | 10.9 GB | 10.8 tok/s | Runs well |
| 60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Apriel 1.5 15B Thinker | Q3_K_M | 11.0 GB | 10.6 tok/s | Runs well |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | UI-Mate 9B | Q4_K_M | 8.1 GB | 13.0 tok/s | Runs well |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | UI-Venus 2 9B | Q4_K_M | 8.1 GB | 13.0 tok/s | Runs well |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 31B | Q2_K | 16.2 GB | 6.4 tok/s | Slowtight fit |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Axion 1.0 35B | Q2_K | 16.3 GB | 55.3 tok/s | Runs welltight fit |
| 64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron Labs Dory 1.0 4B | Q4_K_M | 5.0 GB | 30.7 tok/s | Runs great |
| 64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Magistral Small 2506 | Q4_K_M | 17.8 GB | 5.2 tok/s | Slowtight fit |
| 64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Small 3.2 24B | Q4_K_M | 18.0 GB | 5.1 tok/s | Slowtight fit |
| 58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Phi-4 Reasoning Vision 15B | Q3_K_M | 11.1 GB | 10.4 tok/s | Runs well |
| 58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Phi-4 Reasoning (14B) | Q3_K_M | 10.9 GB | 10.8 tok/s | Runs well |
| 64Good quality (B) · 64 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Reka Flash 3.1 (21B) | Q5_K_M | 18.0 GB | 4.8 tok/s | Slowtight fit |
| 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Devstral Small 2505 | Q4_K_M | 17.8 GB | 5.2 tok/s | Slowtight fit |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | NorthCUA Mini | Q2_K | 16.3 GB | 55.3 tok/s | Runs welltight fit |
| 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Small 3.1 24B | Q4_K_M | 18.0 GB | 5.1 tok/s | Slowtight fit |
| 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Spark-X2.6 4B | Q4_K_M | 4.9 GB | 29.7 tok/s | Runs well |
| 52Fair quality (C) · 52 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.0 H Small (32B-A9B) | Q3_K_M | 18.0 GB | 16.6 tok/s | Runs welltight fit |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V2 Lite Chat | Q4_K_M | 11.9 GB | 43.5 tok/s | Runs great |
| 57Good quality (B) · 57 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 14B | Q3_K_M | 10.7 GB | 10.7 tok/s | Runs well |
| 60Good quality (B) · 60 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 3 27B IT | Q3_K_M | 16.3 GB | 5.8 tok/s | Slowtight fit |
| 44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.0 H Tiny (7B-A1B) | Q8_0 | 9.5 GB | 50.3 tok/s | Runs great |
| 60Good quality (B) · 60 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Small 3 24B (2501) | Q4_K_M | 17.8 GB | 5.2 tok/s | Slowtight fit |
| 55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Apriel Nemotron 15B Thinker | Q3_K_M | 11.1 GB | 10.6 tok/s | Runs well |
| 58Good quality (B) · 58 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM5 2B | Q5_K_M | 4.2 GB | 40.1 tok/s | Runs great |
| 55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | AceReason Nemotron 14B | Q3_K_M | 10.9 GB | 10.7 tok/s | Runs well |
| 55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | OpenReasoning Nemotron 14B | Q3_K_M | 10.9 GB | 10.7 tok/s | Runs well |
| 55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 Coder 14B Instruct | Q3_K_M | 10.9 GB | 10.7 tok/s | Runs well |
| 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-VL 8B Instruct | Q4_K_M | 8.6 GB | 13.9 tok/s | Runs well |
| 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | InternVL3.5 8B | Q4_K_M | 8.5 GB | 14.3 tok/s | Runs well |
| 58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | MedGemma 27B Text IT | Q3_K_M | 16.1 GB | 5.8 tok/s | Slowtight fit |
| 55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Hermes 4 14B | Q3_K_M | 10.6 GB | 10.7 tok/s | Runs well |
| 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek R1 0528 Qwen3 8B | Q4_K_M | 8.3 GB | 14.9 tok/s | Runs well |
| 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Codestral 22B | Q4_K_M | 17.5 GB | 5.5 tok/s | Slowtight fit |
| 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 3 12B IT | Q4_K_M | 10.2 GB | 10.0 tok/s | Runs well |
| 55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Ministral 3 14B Reasoning | Q3_K_M | 10.2 GB | 11.3 tok/s | Runs well |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | InternVL3 14B | Q3_K_M | 11.1 GB | 10.4 tok/s | Runs well |
| 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Dolphin Mistral 24B Venice Edition | Q4_K_M | 18.0 GB | 5.1 tok/s | Slowtight fit |
| 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Voxtral Small 24B | Q4_K_M | 18.2 GB | 5.0 tok/s | Slowtight fit |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Phi-4 (14B) | Q3_K_M | 10.9 GB | 10.7 tok/s | Runs well |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | DeepCoder 14B Preview | Q3_K_M | 10.9 GB | 10.7 tok/s | Runs well |
| 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.1 8B | Q4_K_M | 8.8 GB | 13.9 tok/s | Runs well |
| 57Good quality (B) · 57 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | EXAONE 4.5 33B | Q2_K | 16.5 GB | 5.8 tok/s | Slowtight fit |
| 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Mage-VL-Cowork 4.7B | Q4_K_M | 6.2 GB | 25.8 tok/s | Runs well |
| 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-V 4.5 8B | Q4_K_M | 8.6 GB | 14.0 tok/s | Runs well |
| 57Good quality (B) · 57 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Terminal RSI 27B | Q3_K_M | 16.2 GB | 5.7 tok/s | Slowtight fit |
| 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 8B | Q4_K_M | 8.3 GB | 14.9 tok/s | Runs well |
| 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Solar Pro Preview 22B | Q4_K_M | 16.9 GB | 5.5 tok/s | Slowtight fit |
| 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 4B | Q4_K_M | 5.2 GB | 26.2 tok/s | Runs well |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Ministral 3 14B | Q3_K_M | 10.2 GB | 11.3 tok/s | Runs well |
| 56Good quality (B) · 56 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Hemmingway 1.5 | Q3_K_M | 15.8 GB | 5.9 tok/s | Slowtight fit |
| 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Dolphin 3.0 R1 Mistral 24B | Q4_K_M | 17.8 GB | 5.2 tok/s | Slowtight fit |
| 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | TMax 4B | Q4_K_M | 4.9 GB | 29.0 tok/s | Runs well |
| 52Fair quality (C) · 52 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek R1 Distill Qwen 14B | Q3_K_M | 10.9 GB | 10.7 tok/s | Runs well |
| 52Fair quality (C) · 52 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 14B Instruct | Q3_K_M | 10.9 GB | 10.7 tok/s | Runs well |
| 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4.1V 9B Thinking | Q4_K_M | 8.7 GB | 11.9 tok/s | Runs well |
| 52Fair quality (C) · 52 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | JanusCoder 14B | Q3_K_M | 10.6 GB | 10.7 tok/s | Runs well |
| 55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | SenseNova 6.8 Code2Video | Q3_K_M | 16.0 GB | 5.8 tok/s | Slowtight fit |
| 55Good quality (B) · 55 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | LFM3 1.7B | Q6_K | 3.6 GB | 49.0 tok/s | Runs great |
| 54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | QwQ 32B | Q2_K | 17.3 GB | 6.1 tok/s | Slowtight fit |
| 55Good quality (B) · 55 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | MiMo-VL 7B RL | Q4_K_M | 8.3 GB | 14.7 tok/s | Runs well |
| 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Agents-A1 4B | Q4_K_M | 5.1 GB | 26.9 tok/s | Runs well |
| 54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-VL 32B Instruct | Q2_K | 17.6 GB | 6.0 tok/s | Slowtight fit |
| 55Good quality (B) · 55 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | LLM4Decompile 22B V2 | Q4_K_M | 17.5 GB | 5.5 tok/s | Slowtight fit |
| 55Good quality (B) · 55 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Seed-Coder 8B Reasoning | Q4_K_M | 8.2 GB | 14.8 tok/s | Runs well |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 4B Thinking 2507 | Q4_K_M | 5.7 GB | 30.4 tok/s | Runs great |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 14B Instruct 1M | Q3_K_M | 10.9 GB | 10.7 tok/s | Runs well |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.2 30B | Q2_K | 15.9 GB | 6.9 tok/s | Slowtight fit |
| 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron Nano 9B v2 | Q4_K_M | 7.6 GB | 13.7 tok/s | Runs well |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Olmo 3.1 32B Think | Q2_K | 15.7 GB | 6.2 tok/s | Slowtight fit |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | OpenReasoning Nemotron 32B | Q2_K | 17.3 GB | 6.1 tok/s | Slowtight fit |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Skywork OR1 32B | Q2_K | 17.3 GB | 6.1 tok/s | Slowtight fit |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 32B | Q2_K | 17.3 GB | 6.1 tok/s | Slowtight fit |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Mage-VL 4.7B | Q4_K_M | 6.2 GB | 25.8 tok/s | Runs well |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Ministral 3 8B | Q4_K_M | 8.6 GB | 13.7 tok/s | Runs well |
| 55Good quality (B) · 55 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | GLM-Z1 9B (0414) | Q4_K_M | 8.1 GB | 13.0 tok/s | Runs well |
| 55Good quality (B) · 55 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Fara 1.5 4B | Q4_K_M | 5.1 GB | 26.9 tok/s | Runs well |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | MiMo 7B RL | Q4_K_M | 8.0 GB | 15.6 tok/s | Runs well |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Nemo 12B Instruct | Q4_K_M | 10.8 GB | 10.0 tok/s | Runs well |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Seed-Coder 8B Instruct | Q4_K_M | 8.2 GB | 14.8 tok/s | Runs well |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 4B Instruct 2507 | Q4_K_M | 5.7 GB | 30.4 tok/s | Runs great |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | EXAONE Deep 7.8B | Q4_K_M | 7.9 GB | 15.6 tok/s | Runs well |
| 37Basic quality (D) · 37 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | LFM2 8B-A1B | Q6_K | 9.0 GB | 47.0 tok/s | Runs great |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | EXAONE Deep 32B | Q2_K | 17.0 GB | 6.3 tok/s | Slowtight fit |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4 32B 0414 | Q2_K | 15.6 GB | 6.2 tok/s | Slowtight fit |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | GLM-Z1 32B (0414) | Q2_K | 15.6 GB | 6.2 tok/s | Slowtight fit |
| 52Fair quality (C) · 52 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 2 27B IT | Q3_K_M | 17.1 GB | 5.8 tok/s | Slowtight fit |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-VL 4B Instruct | Q4_K_M | 6.0 GB | 27.5 tok/s | Runs well |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.1 30B | Q2_K | 15.8 GB | 7.0 tok/s | Slowtight fit |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Olmo 3 7B Think | Q4_K_M | 8.0 GB | 16.7 tok/s | Runs well |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Falcon 3 10B Instruct | Q4_K_M | 9.7 GB | 11.9 tok/s | Runs well |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Small 22B (2409) | Q4_K_M | 17.5 GB | 5.5 tok/s | Slowtight fit |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | EXAONE 4.0 32B | Q2_K | 15.6 GB | 6.3 tok/s | Slowtight fit |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Olmo 3.1 32B Instruct | Q2_K | 15.7 GB | 6.2 tok/s | Slowtight fit |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | InternVL3 8B | Q4_K_M | 7.4 GB | 15.4 tok/s | Runs well |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek R1 Distill Qwen 32B | Q2_K | 17.3 GB | 6.1 tok/s | Slowtight fit |
| 44Fair quality (C) · 44 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Unlimited OCR 2 (3B-A0.6B) | Q8_0 | 6.1 GB | 74.4 tok/s | Runs great |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.1 Nemotron Nano 8B v1 | Q4_K_M | 8.0 GB | 15.2 tok/s | Runs well |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Falcon-H1R 7B | Q4_K_M | 7.1 GB | 16.1 tok/s | Runs well |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.2 3B | Q4_K_M | 5.0 GB | 33.4 tok/s | Runs great |
| 52Fair quality (C) · 52 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 Coder 7B Instruct | Q4_K_M | 7.2 GB | 16.0 tok/s | Runs well |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | LFM3-VL 2B | Q6_K | 3.7 GB | 44.2 tok/s | Runs great |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Baichuan M2 32B | Q2_K | 17.3 GB | 6.1 tok/s | Slowtight fit |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | OpenHands LM 32B | Q2_K | 17.3 GB | 6.1 tok/s | Slowtight fit |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 32B Instruct | Q2_K | 17.3 GB | 6.1 tok/s | Slowtight fit |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 2 9B IT | Q4_K_M | 9.3 GB | 13.2 tok/s | Runs well |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 4B | Q4_K_M | 5.7 GB | 30.4 tok/s | Runs great |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | OpenReasoning Nemotron 7B | Q4_K_M | 7.2 GB | 16.0 tok/s | Runs well |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Foundation-Sec 8B Reasoning | Q4_K_M | 8.0 GB | 15.2 tok/s | Runs well |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 3n E4B | Q4_K_M | 7.0 GB | 30.6 tok/s | Runs great |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Hunyuan 7B Instruct | Q4_K_M | 7.7 GB | 16.3 tok/s | Runs well |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM4 8B | Q4_K_M | 7.3 GB | 14.9 tok/s | Runs well |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-VL 32B Instruct | Q2_K | 17.6 GB | 6.0 tok/s | Slowtight fit |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Qianfan-OCR 4B | Q4_K_M | 6.2 GB | 25.8 tok/s | Runs well |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Olmo 3 7B Instruct | Q4_K_M | 8.0 GB | 16.7 tok/s | Runs well |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4 9B 0414 | Q4_K_M | 8.1 GB | 13.0 tok/s | Runs well |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-o 2.6 8B | Q4_K_M | 7.8 GB | 14.1 tok/s | Runs well |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | NorthCUA Nano | Q4_K_M | 8.1 GB | 13.0 tok/s | Runs well |
| 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 Coder 32B Instruct | Q2_K | 17.3 GB | 6.1 tok/s | Slowtight fit |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-VL 7B Instruct | Q4_K_M | 7.6 GB | 14.7 tok/s | Runs well |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 7B Instruct | Q4_K_M | 7.2 GB | 16.0 tok/s | Runs well |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | InternVL2.5 8B | Q4_K_M | 8.1 GB | 15.1 tok/s | Runs well |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek R1 Distill Llama 8B | Q4_K_M | 8.0 GB | 15.2 tok/s | Runs well |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Foundation-Sec 1.1 8B Instruct | Q4_K_M | 8.0 GB | 15.2 tok/s | Runs well |
| 24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek MoE 16B Chat | Q4_K_M | 13.0 GB | 38.1 tok/s | Runs great |
| 40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Unlimited OCR (3B-A0.6B) | Q8_0 | 6.1 GB | 74.4 tok/s | Runs great |
| 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | QwQ 32B Preview | Q2_K | 17.3 GB | 6.1 tok/s | Slowtight fit |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3 Nano 4B | Q4_K_M | 4.6 GB | 30.8 tok/s | Runs great |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | North Micro Vision | Q5_K_M | 4.8 GB | 40.7 tok/s | Runs great |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3.5 Mini Instruct | Q4_K_M | 7.6 GB | 32.0 tok/s | Runs great |
| 22Basic quality (D) · 22 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Qwen1.5 MoE A2.7B Chat | Q4_K_M | 12.4 GB | 39.3 tok/s | Runs great |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | InternLM3 8B Instruct | Q4_K_M | 7.8 GB | 13.9 tok/s | Runs well |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek Prover V2 7B | Q4_K_M | 10.3 GB | 17.7 tok/s | Runs well |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Fara 7B | Q4_K_M | 7.6 GB | 14.7 tok/s | Runs well |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Phi-4 Mini Reasoning (3.8B) | Q4_K_M | 5.5 GB | 31.8 tok/s | Runs great |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.1 3B | Q4_K_M | 4.8 GB | 35.9 tok/s | Runs great |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 7B Instruct 1M | Q4_K_M | 7.2 GB | 16.0 tok/s | Runs well |
| 44Fair quality (C) · 44 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Falcon-H1 34B Instruct | Q2_K | 16.7 GB | 6.0 tok/s | Slowtight fit |
| 45Fair quality (C) · 45 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Hermes 3 (Llama 3.1 8B) | Q4_K_M | 8.0 GB | 15.2 tok/s | Runs well |
| 45Fair quality (C) · 45 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.1 8B Instruct | Q4_K_M | 8.0 GB | 15.2 tok/s | Runs well |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Falcon-H1 7B Instruct | Q4_K_M | 7.1 GB | 16.1 tok/s | Runs well |
| 45Fair quality (C) · 45 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4 9B Chat 1M | Q4_K_M | 8.5 GB | 12.9 tok/s | Runs well |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | GLiDE 9B | Q4_K_M | 7.2 GB | 15.4 tok/s | Runs well |
| 36Basic quality (D) · 36 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | OLMo 2 13B Instruct | Q3_K_M | 12.1 GB | 11.5 tok/s | Runs well |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.2 8B Instruct | Q4_K_M | 8.4 GB | 15.0 tok/s | Runs well |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.3 8B | Q4_K_M | 8.4 GB | 15.0 tok/s | Runs well |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Command R (08-2024) 32B | Q2_K | 16.3 GB | 6.2 tok/s | Slowtight fit |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 3n E2B | Q6_K | 6.6 GB | 42.4 tok/s | Runs great |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Pixtral 12B (2409) | Q3_K_M | 9.5 GB | 12.7 tok/s | Runs well |
| 45Fair quality (C) · 45 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4 9B Chat (2024) | Q4_K_M | 8.1 GB | 13.0 tok/s | Runs well |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Apertus v1.5 8B | Q4_K_M | 8.6 GB | 13.7 tok/s | Runs well |
| 45Fair quality (C) · 45 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | LightOnOCR-3 4B | Q4_K_M | 5.1 GB | 26.9 tok/s | Runs well |
| 26Basic quality (D) · 26 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | OLMoE 1B-7B Instruct | Q8_0 | 9.9 GB | 40.5 tok/s | Runs great |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Ministral 8B (2410) | Q4_K_M | 8.2 GB | 15.2 tok/s | Runs well |
| 45Fair quality (C) · 45 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-V 2.6 8B | Q4_K_M | 7.5 GB | 15.1 tok/s | Runs well |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-Omni 7B | Q4_K_M | 9.1 GB | 11.4 tok/s | Runs well |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Phi-4 Mini (3.8B) | Q4_K_M | 5.5 GB | 31.8 tok/s | Runs great |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | DeepHermes 3 Llama 3 8B Preview | Q4_K_M | 8.0 GB | 15.2 tok/s | Runs well |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Dolphin 3.0 Llama 3.1 8B | Q4_K_M | 8.0 GB | 15.2 tok/s | Runs well |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Tülu 3 8B | Q4_K_M | 8.0 GB | 15.2 tok/s | Runs well |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | EXAONE 3.5 7.8B | Q4_K_M | 7.9 GB | 15.6 tok/s | Runs well |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | WeVisOne-VL 4B | Q4_K_M | 6.2 GB | 25.3 tok/s | Runs well |
| 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3.5 Vision Instruct | Q4_K_M | 7.8 GB | 29.4 tok/s | Runs well |
| 45Fair quality (C) · 45 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Chandra OCR 2 | Q4_K_M | 5.6 GB | 23.1 tok/s | Runs well |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Ministral 3 3B | Q4_K_M | 5.3 GB | 31.7 tok/s | Runs great |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | LFM2.5-VL 3B | Q4_K_M | 4.1 GB | 39.2 tok/s | Runs great |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | OLMo 2 32B Instruct | Q2_K | 16.0 GB | 6.2 tok/s | Slowtight fit |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Falcon 3 7B Instruct | Q4_K_M | 7.5 GB | 16.4 tok/s | Runs well |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Aya Expanse 32B | Q2_K | 16.3 GB | 6.2 tok/s | Slowtight fit |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3 Medium 128K Instruct | Q3_K_M | 10.6 GB | 11.3 tok/s | Runs well |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Aya Vision 32B | Q2_K | 16.7 GB | 6.1 tok/s | Slowtight fit |
| 40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | TeleOCR | Q8_0 | 4.5 GB | 43.8 tok/s | Runs great |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | LFM2.5 2.6B | Q4_K_M | 3.8 GB | 45.3 tok/s | Runs great |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | SmolLM3 3B | Q4_K_M | 4.5 GB | 39.7 tok/s | Runs great |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.1 Nemotron Nano 4B v1.1 | Q4_K_M | 5.9 GB | 27.1 tok/s | Runs well |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.1 8B Instruct | Q4_K_M | 8.4 GB | 15.0 tok/s | Runs well |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Jamba Reasoning 3B | Q4_K_M | 4.0 GB | 38.2 tok/s | Runs great |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.2 11B Vision Instruct | Q4_K_M | 9.9 GB | 11.5 tok/s | Runs well |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | CodeGeeX4 All 9B | Q4_K_M | 8.1 GB | 13.0 tok/s | Runs well |
| 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3 Mini 128K Instruct | Q4_K_M | 7.6 GB | 32.0 tok/s | Runs great |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-OCR 1.0 1.3B | Q8_0 | 3.5 GB | 47.9 tok/s | Runs great |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek R1 Distill Qwen 7B | Q4_K_M | 7.2 GB | 16.0 tok/s | Runs well |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | InternVL2 8B | Q4_K_M | 8.1 GB | 15.1 tok/s | Runs well |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Dolphin 2.9.4 Llama 3.1 8B | Q4_K_M | 8.0 GB | 15.2 tok/s | Runs well |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Hermes 2 Pro Llama 3 8B | Q4_K_M | 8.0 GB | 15.2 tok/s | Runs well |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | OpenChat 3.6 8B | Q4_K_M | 8.0 GB | 15.2 tok/s | Runs well |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Phi-4 Multimodal Instruct | Q4_K_M | 6.5 GB | 21.9 tok/s | Runs well |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3 Small 8K Instruct | Q4_K_M | 7.6 GB | 16.5 tok/s | Runs well |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Hunyuan 4B Instruct | Q4_K_M | 5.8 GB | 29.0 tok/s | Runs well |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 3 4B IT | Q4_K_M | 4.9 GB | 28.4 tok/s | Runs well |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | PaddleOCR-VL 1.6 0.9B | Q8_0 | 3.2 GB | 64.8 tok/s | Runs great |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | InternLM2.5 20B Chat | Q2_K | 11.6 GB | 10.1 tok/s | Runs well |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Jamba2 3B | Q4_K_M | 3.9 GB | 40.3 tok/s | Runs great |
| 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek Coder 6.7B Instruct | Q4_K_M | 10.5 GB | 18.1 tok/s | Runs well |
| 40Fair quality (C) · 40 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-V 4.7 1B | Q8_0 | 3.8 GB | 40.1 tok/s | Runs great |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Mistral-NeMo-Minitron 8B Instruct | Q4_K_M | 8.5 GB | 14.5 tok/s | Runs well |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3 Medium (14B) | Q3_K_M | 9.7 GB | 11.3 tok/s | Runs well |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | MedGemma 4B IT | Q4_K_M | 4.9 GB | 28.4 tok/s | Runs well |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2-VL 7B Instruct | Q4_K_M | 7.6 GB | 14.7 tok/s | Runs well |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | TMax 2B | Q6_K | 3.7 GB | 45.1 tok/s | Runs great |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Aya Vision 8B | Q4_K_M | 7.7 GB | 14.2 tok/s | Runs well |
| 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | CodeGemma 7B | Q4_K_M | 11.0 GB | 14.3 tok/s | Runs well |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.0 Micro (3B) | Q4_K_M | 4.8 GB | 35.9 tok/s | Runs great |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2 7B Instruct | Q4_K_M | 7.2 GB | 16.0 tok/s | Runs well |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3 8B Instruct | Q4_K_M | 8.0 GB | 15.2 tok/s | Runs well |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Command R7B | Q4_K_M | 7.3 GB | 15.2 tok/s | Runs well |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 2B | Q5_K_M | 3.8 GB | 44.5 tok/s | Runs great |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | LLM4Decompile 6.7B V2 | Q4_K_M | 10.5 GB | 18.1 tok/s | Runs well |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Nous Hermes 2 SOLAR 10.7B | Q4_K_M | 9.4 GB | 11.4 tok/s | Runs well |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | SOLAR 10.7B Instruct | Q4_K_M | 9.4 GB | 11.4 tok/s | Runs well |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-VL 2B Instruct | Q6_K | 4.7 GB | 39.8 tok/s | Runs great |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3 Vision 128K Instruct | Q3_K_M | 7.3 GB | 38.1 tok/s | Runs great |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Apertus 8B Instruct | Q4_K_M | 8.0 GB | 15.2 tok/s | Runs well |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Aya Expanse 8B | Q4_K_M | 8.0 GB | 15.2 tok/s | Runs well |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Command R7B Arabic | Q4_K_M | 7.3 GB | 15.2 tok/s | Runs well |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | InternLM2.5 7B Chat | Q4_K_M | 7.9 GB | 15.8 tok/s | Runs well |
| 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3 Mini 4K Instruct | Q4_K_M | 6.0 GB | 32.0 tok/s | Runs great |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Yi Coder 9B Chat | Q4_K_M | 8.3 GB | 13.8 tok/s | Runs well |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | AFM 4.5B | Q4_K_M | 5.5 GB | 26.5 tok/s | Runs well |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | SQLCoder 7B v2 | Q4_K_M | 10.5 GB | 18.1 tok/s | Runs well |
| 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.0 H Micro | Q4_K_M | 4.1 GB | 38.3 tok/s | Runs great |
| 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | OLMo 2 7B Instruct | Q4_K_M | 8.7 GB | 16.7 tok/s | Runs well |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.0 8B Instruct | Q4_K_M | 7.7 GB | 15.0 tok/s | Runs well |
| 33Basic quality (D) · 33 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.2 3B Instruct | Q4_K_M | 5.0 GB | 38.1 tok/s | Runs great |
| 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 Coder 3B Instruct | Q4_K_M | 4.2 GB | 39.5 tok/s | Runs great |
| 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | Dolphin 2.9 Llama 3 8B | Q4_K_M | 8.0 GB | 15.2 tok/s | Runs well |
| 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | Mistral 7B Instruct v0.3 | Q4_K_M | 7.6 GB | 16.9 tok/s | Runs well |
| 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | Falcon-H1 3B Instruct | Q4_K_M | 4.2 GB | 38.8 tok/s | Runs great |
| 36Basic quality (D) · 36 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM5 1B | Q8_0 | 3.4 GB | 57.6 tok/s | Runs great |
| 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | LLM4Decompile 9B V2 | Q4_K_M | 8.3 GB | 13.8 tok/s | Runs well |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | Yi 1.5 34B Chat | Q2_K | 16.8 GB | 5.8 tok/s | Slowtight fit |
| 29Basic quality (D) · 29 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | InternLM2 Chat 20B | Q2_K | 11.6 GB | 10.1 tok/s | Runs well |
| 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM3 4B | Q4_K_M | 4.8 GB | 30.0 tok/s | Runs great |
| 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | Zamba2 7B Instruct | Q4_K_M | 7.3 GB | 16.6 tok/s | Runs well |
| 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | Voxtral Mini 3B | Q4_K_M | 5.9 GB | 26.1 tok/s | Runs well |
| 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | EXAONE 3.0 7.8B Instruct | Q4_K_M | 7.4 GB | 15.6 tok/s | Runs well |
| 26Basic quality (D) · 26 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 1.1 7B IT | Q4_K_M | 11.0 GB | 14.3 tok/s | Runs well |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | InternLM2 Math Plus 20B | Q2_K | 11.6 GB | 10.1 tok/s | Runs well |
| 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 3B Instruct | Q4_K_M | 4.2 GB | 39.5 tok/s | Runs great |
| 32Basic quality (D) · 32 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | LFM2 2.6B | Q5_K_M | 4.0 GB | 39.3 tok/s | Runs great |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Qwen1.5 14B Chat | Q3_K_M | 15.7 GB | 11.1 tok/s | Runs welltight fit |
| 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Hermes 2 Pro Mistral 7B | Q4_K_M | 7.5 GB | 16.9 tok/s | Runs well |
| 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Starling LM 7B Beta | Q4_K_M | 7.5 GB | 16.9 tok/s | Runs well |
| 25Basic quality (D) · 25 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Code Llama 13B Instruct | Q3_K_M | 15.1 GB | 12.1 tok/s | Runs well |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Hermes 3 Llama 3.2 3B | Q4_K_M | 5.0 GB | 38.1 tok/s | Runs great |
| 26Basic quality (D) · 26 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | CogVLM2 Llama 3 Chat 19B | Q2_K | 14.2 GB | 10.3 tok/s | Runs well |
| 33Basic quality (D) · 33 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Raon 1 nano | Q4_K_M | 4.4 GB | 34.6 tok/s | Runs great |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | S5 nano | Q4_K_M | 5.2 GB | 26.2 tok/s | Runs well |
| 29Basic quality (D) · 29 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 1.7B | Q6_K | 4.7 GB | 41.8 tok/s | Runs great |
| 33Basic quality (D) · 33 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | OpenChat 3.5 (0106) | Q4_K_M | 7.5 GB | 16.9 tok/s | Runs well |
| 36Basic quality (D) · 36 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Falcon3 Mamba 7B Instruct | Q4_K_M | 6.5 GB | 16.8 tok/s | Runs well |
| 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Yi 1.5 9B Chat | Q4_K_M | 7.8 GB | 13.8 tok/s | Runs well |
| 24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 7B IT | Q4_K_M | 11.0 GB | 14.3 tok/s | Runs well |
| 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-VL 3B Instruct | Q4_K_M | 4.6 GB | 32.6 tok/s | Runs great |
| 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Aya 23 8B | Q4_K_M | 8.0 GB | 15.2 tok/s | Runs well |
| 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Mathstral 7B | Q4_K_M | 7.6 GB | 16.9 tok/s | Runs well |
| 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Mistral 7B Instruct v0.2 | Q4_K_M | 7.5 GB | 16.9 tok/s | Runs well |
| 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Nous Hermes 2 Mistral 7B DPO | Q4_K_M | 7.5 GB | 16.9 tok/s | Runs well |
| 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | OpenChat 3.5 (1210) | Q4_K_M | 7.5 GB | 16.9 tok/s | Runs well |
| 29Basic quality (D) · 29 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.2 2B Instruct | Q5_K_M | 4.5 GB | 39.9 tok/s | Runs great |
| 29Basic quality (D) · 29 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.3 2B | Q5_K_M | 4.5 GB | 39.9 tok/s | Runs great |
| 23Basic quality (D) · 23 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Orca 2 13B | Q3_K_M | 11.8 GB | 12.1 tok/s | Runs well |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Qwen1.5 32B Chat | Q2_K | 17.2 GB | 6.2 tok/s | Slowtight fit |
| 32Basic quality (D) · 32 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | LFM2.5 1.2B Instruct | Q8_0 | 3.4 GB | 53.2 tok/s | Runs great |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek Coder 33B Instruct | Q2_K | 17.5 GB | 6.0 tok/s | Slowtight fit |
| 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-Math 7B Instruct | Q4_K_M | 6.9 GB | 16.0 tok/s | Runs well |
| 29Basic quality (D) · 29 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | EXAONE 3.5 2.4B | Q5_K_M | 4.4 GB | 41.9 tok/s | Runs great |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | LLaVA 1.6 34B | Q2_K | 17.0 GB | 5.8 tok/s | Slowtight fit |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | EXAONE 4.0 1.2B | Q8_0 | 3.9 GB | 48.6 tok/s | Runs great |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Falcon 3 3B Instruct | Q4_K_M | 4.8 GB | 37.8 tok/s | Runs great |
| 21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Qwen1.5 7B Chat | Q3_K_M | 10.1 GB | 20.5 tok/s | Runs well |
| 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Codestral Mamba 7B | Q4_K_M | 6.5 GB | 16.8 tok/s | Runs well |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Granite Code 8B Instruct (128K) | Q4_K_M | 8.2 GB | 15.2 tok/s | Runs well |
| 32Basic quality (D) · 32 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | RecurrentGemma 9B IT | Q4_K_M | 8.0 GB | 12.7 tok/s | Runs well |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | InternLM2 Math Plus 7B | Q4_K_M | 7.9 GB | 15.8 tok/s | Runs well |
| 21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Llama 2 13B Chat | Q3_K_M | 11.8 GB | 12.1 tok/s | Runs well |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | OpenHermes 2.5 Mistral 7B | Q4_K_M | 7.5 GB | 16.9 tok/s | Runs well |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Starling LM 7B Alpha | Q4_K_M | 7.5 GB | 16.9 tok/s | Runs well |
| 27Basic quality (D) · 27 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.1 2B Instruct | Q5_K_M | 4.5 GB | 39.9 tok/s | Runs great |
| 21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Baichuan 2 13B Chat | Q3_K_M | 12.2 GB | 11.4 tok/s | Runs well |
| 20Basic quality (D) · 20 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Code Llama 7B Instruct | Q3_K_M | 9.7 GB | 23.4 tok/s | Runs well |
| 26Basic quality (D) · 26 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | WeVisOne VL 2B | Q5_K_M | 4.7 GB | 41.4 tok/s | Runs great |
| 27Basic quality (D) · 27 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 2 2B | Q5_K_M | 4.4 GB | 38.7 tok/s | Runs great |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | StarCoder2 15B Instruct | Q2_K | 9.1 GB | 12.6 tok/s | Runs well |
| 26Basic quality (D) · 26 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | StableLM 2 12B Chat | Q4_K_M | 10.3 GB | 10.1 tok/s | Runs well |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Granite Code 34B Instruct | Q2_K | 15.9 GB | 6.0 tok/s | Slowtight fit |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Yi 34B Chat | Q2_K | 16.8 GB | 5.8 tok/s | Slowtight fit |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Kimi Linear 48B-A3B | Q2_K | 21.8 GB | 47.0 tok/s | Slowfar over GPU memory limit |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.0 H 1B | Q8_0 | 3.7 GB | 42.6 tok/s | Runs great |
| 23Basic quality (D) · 23 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | SmolVLM2 2.2B Instruct | Q5_K_M | 5.3 GB | 44.9 tok/s | Runs great |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Mistral 7B Instruct v0.1 | Q4_K_M | 7.5 GB | 16.9 tok/s | Runs well |
| 25Basic quality (D) · 25 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Granite Code 20B Instruct | Q2_K | 10.3 GB | 10.0 tok/s | Runs well |
| 24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Granite Vision 3.2 2B | Q4_K_M | 4.5 GB | 41.0 tok/s | Runs great |
| 26Basic quality (D) · 26 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Code Llama 34B Instruct | Q2_K | 17.2 GB | 5.9 tok/s | Slowtight fit |
| 19Basic quality (D) · 19 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Stable Code Instruct 3B | Q4_K_M | 6.5 GB | 43.6 tok/s | Runs great |
| 20Basic quality (D) · 20 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.1 3B-A800M Instruct | Q8_0 | 6.1 GB | 60.0 tok/s | Runs great |
| 26Basic quality (D) · 26 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 Coder 1.5B Instruct | Q8_0 | 3.9 GB | 40.4 tok/s | Runs great |
| 26Basic quality (D) · 26 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Falcon-H1 1.5B Instruct | Q8_0 | 3.9 GB | 40.1 tok/s | Runs great |
| 18Basic quality (D) · 18 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | WizardLM 13B v1.2 | Q3_K_M | 11.8 GB | 12.1 tok/s | Runs well |
| 18Basic quality (D) · 18 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | LLaVA 1.5 13B | Q3_K_M | 12.0 GB | 11.8 tok/s | Runs well |
| 25Basic quality (D) · 25 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | DeepScaleR 1.5B Preview | Q6_K | 3.8 GB | 47.6 tok/s | Runs great |
| 26Basic quality (D) · 26 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | LLaVA 1.6 Mistral 7B | Q4_K_M | 7.8 GB | 16.1 tok/s | Runs well |
| 19Basic quality (D) · 19 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Granite Code 3B Instruct (128K) | Q4_K_M | 6.9 GB | 35.1 tok/s | Runs great |
| 21Basic quality (D) · 21 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | SmolVLM 2.2B Instruct | Q5_K_M | 5.3 GB | 44.9 tok/s | Runs great |
| 26Basic quality (D) · 26 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Neural Chat 7B v3.3 | Q4_K_M | 7.5 GB | 16.9 tok/s | Runs well |
| 24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.0 2B Instruct | Q4_K_M | 4.0 GB | 46.5 tok/s | Runs great |
| 26Basic quality (D) · 26 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | LFM2 1.2B | Q8_0 | 3.4 GB | 53.2 tok/s | Runs great |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Falcon Mamba 7B Instruct | Q4_K_M | 6.5 GB | 16.8 tok/s | Runs well |
| 24Basic quality (D) · 24 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 1.5B Instruct | Q8_0 | 3.9 GB | 40.4 tok/s | Runs great |
| 16Basic quality (D) · 16 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Vicuna 13B v1.5 | Q3_K_M | 11.8 GB | 12.1 tok/s | Runs well |
| 26Basic quality (D) · 26 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 0.8B | Q8_0 | 3.1 GB | 71.5 tok/s | Runs great |
| 18Basic quality (D) · 18 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.0 3B-A800M Instruct | Q8_0 | 5.9 GB | 60.0 tok/s | Runs great |
| 25Basic quality (D) · 25 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-Omni 3B | Q3_K_M | 5.1 GB | 28.5 tok/s | Runs well |
| 23Basic quality (D) · 23 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2-VL 2B Instruct | Q5_K_M | 3.9 GB | 45.7 tok/s | Runs great |
| 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Seed-OSS 36B Instruct | Q2_K | 18.7 GB | 4.7 tok/s | Slowover GPU memory limit |
| 19Basic quality (D) · 19 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | SmolLM2 1.7B Instruct | Q6_K | 5.1 GB | 49.6 tok/s | Runs great |
| 23Basic quality (D) · 23 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | LFM2-VL 1.6B | Q6_K | 3.5 GB | 53.7 tok/s | Runs great |
| 55Good quality (B) · 55 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Hermes 4.3 36B | Q2_K | 18.7 GB | 4.7 tok/s | Slowover GPU memory limit |
| 22Basic quality (D) · 22 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | StarCoder2 15B (base) | Q2_K | 9.1 GB | 12.6 tok/s | Runs well |
| 21Basic quality (D) · 21 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Hunyuan 1.8B Instruct | Q6_K | 4.1 GB | 47.4 tok/s | Runs great |
| 21Basic quality (D) · 21 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek R1 Distill Qwen 1.5B | Q6_K | 3.8 GB | 47.6 tok/s | Runs great |
| 20Basic quality (D) · 20 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Zamba2 2.7B Instruct | Q4_K_M | 4.1 GB | 45.9 tok/s | Runs great |
| 22Basic quality (D) · 22 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.2 1B Instruct | Q8_0 | 3.6 GB | 50.2 tok/s | Runs great |
| 23Basic quality (D) · 23 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Yi 1.5 6B Chat | Q3_K_M | 5.3 GB | 26.1 tok/s | Runs well |
| 21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | WizardMath 7B v1.1 | Q3_K_M | 6.7 GB | 21.8 tok/s | Runs well |
| 21Basic quality (D) · 21 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Zephyr 7B Beta | Q3_K_M | 6.7 GB | 21.8 tok/s | Runs well |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3.5 MoE (42B-A6.6B) | Q2_K | 19.9 GB | 23.6 tok/s | Runs wellover GPU memory limit |
| 20Basic quality (D) · 20 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | d1 2B | Q6_K | 3.7 GB | 44.2 tok/s | Runs great |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | InternVL3.5 38B | Q2_K | 19.6 GB | 4.4 tok/s | Slowover GPU memory limit |
| 16Basic quality (D) · 16 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | Yi Coder 1.5B Chat | Q8_0 | 5.2 GB | 42.0 tok/s | Runs great |
| 20Basic quality (D) · 20 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-Math 1.5B Instruct | Q8_0 | 3.8 GB | 40.4 tok/s | Runs great |
| 18Basic quality (D) · 18 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron Mini 4B Instruct | Q3_K_M | 4.6 GB | 37.7 tok/s | Runs great |
| 15Basic quality (D) · 15 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | Orca 2 7B | Q2_K | 6.9 GB | 29.8 tok/s | Runs well |
| 17Basic quality (D) · 17 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | InternLM2.5 1.8B Chat | Q6_K | 4.4 GB | 44.9 tok/s | Runs great |
| 15Basic quality (D) · 15 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | StableLM Zephyr 3B | Q4_K_M | 5.1 GB | 43.6 tok/s | Runs great |
| 20Basic quality (D) · 20 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 3 1B | Q8_0 | 3.2 GB | 62.2 tok/s | Runs great |
| 14Basic quality (D) · 14 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | Llama 2 7B Chat | Q2_K | 6.9 GB | 29.8 tok/s | Runs well |
| 17Basic quality (D) · 17 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | StarCoder2 3B | Q4_K_M | 4.2 GB | 40.3 tok/s | Runs great |
| 20Basic quality (D) · 20 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | StarCoder2 7B | Q3_K_M | 6.1 GB | 22.0 tok/s | Runs well |
| 14Basic quality (D) · 14 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | Baichuan 2 7B Chat | Q2_K | 7.2 GB | 26.7 tok/s | Runs well |
| 18Basic quality (D) · 18 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | StarCoder 15B | Q2_K | 8.6 GB | 12.7 tok/s | Runs well |
| 15Basic quality (D) · 15 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | Phi-2 2.7B | Q4_K_M | 4.4 GB | 44.0 tok/s | Runs great |
| 16Basic quality (D) · 16 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | GLiDE 2B | Q6_K | 3.7 GB | 45.1 tok/s | Runs great |
| 15Basic quality (D) · 15 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | Falcon 3 1B Instruct | Q6_K | 4.0 GB | 50.8 tok/s | Runs great |
| 16Basic quality (D) · 16 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2 1.5B Instruct | Q8_0 | 3.9 GB | 40.4 tok/s | Runs great |
| 12Basic quality (D) · 12 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek LLM 7B Chat | Q2_K | 6.8 GB | 29.0 tok/s | Runs well |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | InternVL3 38B | Q2_K | 19.6 GB | 4.4 tok/s | Slowover GPU memory limit |
| 12Basic quality (D) · 12 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek Coder 1.3B Instruct | Q8_0 | 5.1 GB | 46.1 tok/s | Runs great |
| 12Basic quality (D) · 12 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | LLM4Decompile 1.3B V2 | Q8_0 | 5.1 GB | 46.1 tok/s | Runs great |
| 18Basic quality (D) · 18 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | LFM2 700M | Q8_0 | 2.9 GB | 84.1 tok/s | Runs great |
| 15Basic quality (D) · 15 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | Spark X2.6 1.7B | Q6_K | 3.6 GB | 49.6 tok/s | Runs great |
| 11Basic quality (D) · 11 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | LLaVA 1.5 7B | Q2_K | 7.0 GB | 28.4 tok/s | Runs well |
| 14Basic quality (D) · 14 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | OLMo 2 1B Instruct | Q8_0 | 4.2 GB | 42.0 tok/s | Runs great |
| 15Basic quality (D) · 15 of 100: how capable the model is at F16, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | surya ocr 2.5 | F16 | 3.5 GB | 41.6 tok/s | Runs great |
| 13Basic quality (D) · 13 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | CodeGemma 2B | Q5_K_M | 4.0 GB | 40.2 tok/s | Runs great |
| 13Basic quality (D) · 13 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | SmolLM 1.7B Instruct | Q6_K | 3.9 GB | 49.6 tok/s | Runs great |
| 14Basic quality (D) · 14 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 0.6B | Q8_0 | 3.8 GB | 83.0 tok/s | Runs great |
| 9Basic quality (D) · 9 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | Vicuna 7B v1.5 | Q2_K | 6.9 GB | 29.8 tok/s | Runs well |
| 14Basic quality (D) · 14 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | Yi 6B Chat | Q2_K | 4.8 GB | 33.1 tok/s | Runs great |
| 14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | Falcon-H1 0.5B Instruct | F16 | 3.3 GB | 55.1 tok/s | Runs great |
| 11Basic quality (D) · 11 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 2B IT | Q5_K_M | 4.0 GB | 40.2 tok/s | Runs great |
| 14Basic quality (D) · 14 of 100: how capable the model is at F16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | LFM2.5 350M | F16 | 2.9 GB | 81.9 tok/s | Runs great |
| 9Basic quality (D) · 9 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | StableLM 2 1.6B Chat | Q6_K | 4.2 GB | 51.7 tok/s | Runs great |
| 9Basic quality (D) · 9 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | StableLM 2 Zephyr 1.6B | Q6_K | 4.2 GB | 51.7 tok/s | Runs great |
| 9Basic quality (D) · 9 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | OLMo 7B Instruct | Q2_K | 5.9 GB | 29.1 tok/s | Runs well |
| 12Basic quality (D) · 12 of 100: how capable the model is at F16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | LFM2-VL 450M | F16 | 3.1 GB | 63.7 tok/s | Runs great |
| 12Basic quality (D) · 12 of 100: how capable the model is at F16, whatever it runs on. Match score 49/100 (quality, fit, speed and memory use) sets the ranking. | LFM2 350M | F16 | 2.9 GB | 81.9 tok/s | Runs great |
| 12Basic quality (D) · 12 of 100: how capable the model is at F16, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.0 H 350M | F16 | 2.8 GB | 84.3 tok/s | Runs great |
| 8Basic quality (D) · 8 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | InternLM 7B | Q2_K | 6.1 GB | 27.4 tok/s | Runs well |
| 10Basic quality (D) · 10 of 100: how capable the model is at F16, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | SmolVLM 500M Instruct | F16 | 3.4 GB | 56.2 tok/s | Runs great |
| 11Basic quality (D) · 11 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | GLiDE 0.8B | Q8_0 | 3.0 GB | 83.0 tok/s | Runs great |
| 8Basic quality (D) · 8 of 100: how capable the model is at F16, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | Hunyuan 0.5B Instruct | F16 | 3.9 GB | 53.1 tok/s | Runs great |
| 10Basic quality (D) · 10 of 100: how capable the model is at F16, whatever it runs on. Match score 48/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 0.5B Instruct | F16 | 3.1 GB | 58.5 tok/s | Runs great |
| 10Basic quality (D) · 10 of 100: how capable the model is at F16, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking. | LFM2.5 230M | F16 | 2.6 GB | 125 tok/s | Runs great |
| 8Basic quality (D) · 8 of 100: how capable the model is at F16, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 Coder 0.5B Instruct | F16 | 3.1 GB | 58.5 tok/s | Runs great |
| 8Basic quality (D) · 8 of 100: how capable the model is at F16, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking. | SmolLM2 360M Instruct | F16 | 3.1 GB | 79.6 tok/s | Runs great |
| 6Basic quality (D) · 6 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | TinyLlama 1.1B Chat | Q8_0 | 3.3 GB | 56.6 tok/s | Runs great |
| 6Basic quality (D) · 6 of 100: how capable the model is at F16, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2 0.5B Instruct | F16 | 3.1 GB | 58.5 tok/s | Runs great |
| 6Basic quality (D) · 6 of 100: how capable the model is at F16, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE 4.5 0.3B | F16 | 2.9 GB | 79.6 tok/s | Runs great |
| 6Basic quality (D) · 6 of 100: how capable the model is at F16, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | SmolVLM 256M Instruct | F16 | 2.8 GB | 110 tok/s | Runs great |
| 6Basic quality (D) · 6 of 100: how capable the model is at F16, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 3 270M | F16 | 2.6 GB | 106 tok/s | Runs great |
| 5Basic quality (D) · 5 of 100: how capable the model is at F16, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking. | SmolLM 360M Instruct | F16 | 2.9 GB | 79.6 tok/s | Runs great |
| 4Basic quality (D) · 4 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 45/100 (quality, fit, speed and memory use) sets the ranking. | Falcon 7B Instruct | Q2_K | 5.0 GB | 27.8 tok/s | Runs well |
| 4Basic quality (D) · 4 of 100: how capable the model is at F16, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. | SmolLM2 135M Instruct | F16 | 2.5 GB | 221 tok/s | Runs great |
| 3Basic quality (D) · 3 of 100: how capable the model is at F16, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. | Falcon-H1 Tiny 90M Instruct | F16 | 2.3 GB | 319 tok/s | Runs great |
| 2Basic quality (D) · 2 of 100: how capable the model is at F16, whatever it runs on. Match score 43/100 (quality, fit, speed and memory use) sets the ranking. | SmolLM 135M Instruct | F16 | 2.4 GB | 221 tok/s | Runs great |
| 36Basic quality (D) · 36 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 43/100 (quality, fit, speed and memory use) sets the ranking. | Nous Hermes 2 Mixtral 8x7B DPO | Q2_K | 21.8 GB | 12.6 tok/s | Slowfar over GPU memory limit |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 43/100 (quality, fit, speed and memory use) sets the ranking. | Mixtral 8x7B Instruct | Q2_K | 21.8 GB | 12.6 tok/s | Slowfar over GPU memory limit |
| 11Basic quality (D) · 11 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 34/100 (quality, fit, speed and memory use) sets the ranking. | Falcon 40B Instruct | Q2_K | 19.0 GB | 4.1 tok/s | Slowover GPU memory limit |
| 84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | gpt-oss 120B | MXFP4 | 69.0 GB | — | Won't run |
| 69Good quality (B) · 69 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | Kimi K3.1 Pro (2.8T) | Q2_K | 1,114 GB | — | Won't run |
| 68Good quality (B) · 68 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V4.1 Flash 1017 (552B-A16B) | Q2_K | 307 GB | — | Won't run |
| 68Good quality (B) · 68 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | GLM-5.3 (753B-A40B) | Q2_K | 304 GB | — | Won't run |
| 68Good quality (B) · 68 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.8 Max (2.4T-A95B) | Q2_K | 981 GB | — | Won't run |
| 68Good quality (B) · 68 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | Kimi K3 (2.8T) | Q2_K | 1,114 GB | — | Won't run |
| 68Good quality (B) · 68 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | LongCat 2.5 (1.6T-A48B) | Q2_K | 714 GB | — | Won't run |
| 68Good quality (B) · 68 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | MiMo V2.6 Pro (1T-A42B) | Q2_K | 412 GB | — | Won't run |
| 68Good quality (B) · 68 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | Ling 3.1 Flash 1019 (560B-A25B) | Q2_K | 231 GB | — | Won't run |
| 67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax M3.1 Flash (428B-A23B) | Q2_K | 175 GB | — | Won't run |
| 67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | Nex N2.6 (321B-A18B) | Q2_K | 131 GB | — | Won't run |
| 67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | Step 5 Preview (600B-A27B) | Q2_K | 244 GB | — | Won't run |
| 67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | GLM-5.3 Flash (320B-A18B) | Q2_K | 131 GB | — | Won't run |
| 67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | MiMo V2.6 Flash (310B-A15B) | Q2_K | 127 GB | — | Won't run |
| 67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V4.1 Flash (552B-A16B) | Q2_K | 307 GB | — | Won't run |
| 67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Large 4 (1T-A52B) | Q2_K | 424 GB | — | Won't run |
| 67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.8 Flash Next (125B-A6B) | Q2_K | 74.3 GB | — | Won't run |
| 67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | GLM-5.2 (753B-A40B) | Q2_K | 304 GB | — | Won't run |
| 67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | Hunyuan Hy4 Preview (780B) | Q2_K | 315 GB | — | Won't run |
| 67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | Muse Spark Open (816B-A42B) | Q2_K | 331 GB | — | Won't run |
| 67Good quality (B) · 67 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V4 Pro (1.6T-A49B) | Q2_K | 663 GB | — | Won't run |
| 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | Kimi K2.6 (1T) | Q2_K | 413 GB | — | Won't run |
| 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | Ling 3.1 Flash (560B-A25B) | Q2_K | 231 GB | — | Won't run |
| 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | MiMo V2.5 Pro (1T-A42B) | Q2_K | 412 GB | — | Won't run |
| 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | Intern-S2 (397B-A17B) | Q2_K | 164 GB | — | Won't run |
| 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | GLM-5.1 (744B-A40B) | Q2_K | 304 GB | — | Won't run |
| 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Nex N2 Pro (397B-A17B) | Q2_K | 161 GB | — | Won't run |
| 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V4 Pro (April 2026) | Q2_K | 642 GB | — | Won't run |
| 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Naive N0.5 Flash (309B-A15.5B) | Q2_K | 126 GB | — | Won't run |
| 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 397B-A17B | Q2_K | 164 GB | — | Won't run |
| 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax M3 (427B) | Q2_K | 174 GB | — | Won't run |
| 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | GLM-5 (744B-A40B) | Q2_K | 304 GB | — | Won't run |
| 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | K2-Horizon (375B-A23B) | Q2_K | 156 GB | — | Won't run |
| 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Hunyuan Hy3 (295B-A21B) | Q2_K | 124 GB | — | Won't run |
| 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Beam 1.0 (501B-A23B) | Q2_K | 203 GB | — | Won't run |
| 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Kimi K2.5 (1T) | Q2_K | 413 GB | — | Won't run |
| 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Kimi K2.7 Code (1T) | Q2_K | 413 GB | — | Won't run |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V4 Flash (284B-A13B) | Q2_K | 124 GB | — | Won't run |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | MiMo V2.5 (310B-A15B) | Q2_K | 127 GB | — | Won't run |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.5 397B-A17B | Q2_K | 164 GB | — | Won't run |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3.5 Super VL 120B-A12B | Q2_K | 51.9 GB | — | Won't run |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V3.2 (671B) | Q2_K | 277 GB | — | Won't run |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Inkling Small (276B-A12B) | Q2_K | 109 GB | — | Won't run |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4.7 (355B-A32B) | Q2_K | 148 GB | — | Won't run |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Inkling (975B-A41B) | Q2_K | 383 GB | — | Won't run |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax M2.7 (230B-A10B) | Q2_K | 95.6 GB | — | Won't run |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Step 3.7 Flash (198B-A11B) | Q2_K | 83.0 GB | — | Won't run |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3 Ultra 550B-A55B | Q2_K | 226 GB | — | Won't run |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek R1 0528 (671B) | Q2_K | 276 GB | — | Won't run |
| 65Good quality (B) · 65 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Kimi K2 Thinking (1T) | Q2_K | 413 GB | — | Won't run |
| 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.5 122B-A10B | Q2_K | 52.3 GB | — | Won't run |
| 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V3.2 Exp | Q2_K | 277 GB | — | Won't run |
| 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Ling 2.6 1T | Q2_K | 412 GB | — | Won't run |
| 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax M2.5 (230B-A10B) | Q2_K | 95.6 GB | — | Won't run |
| 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3.5 Bolt 74B-A9B | Q2_K | 32.1 GB | — | Won't run |
| 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek R1 (671B) | Q2_K | 271 GB | — | Won't run |
| 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V4 Flash (April 2026) | Q2_K | 119 GB | — | Won't run |
| 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 122B-A10B | Q2_K | 52.3 GB | — | Won't run |
| 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Step 3.5 Flash (196B-A11B) | Q2_K | 82.2 GB | — | Won't run |
| 64Good quality (B) · 64 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V3.1 Terminus | Q2_K | 276 GB | — | Won't run |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V3.1 (671B) | Q2_K | 276 GB | — | Won't run |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Kimi K2 Instruct 0905 (1T) | Q2_K | 413 GB | — | Won't run |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Kolibri 1 (78B-A3.5B) | Q2_K | 33.5 GB | — | Won't run |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax M2.1 (230B-A10B) | Q2_K | 95.6 GB | — | Won't run |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 235B-A22B Thinking 2507 | Q2_K | 97.7 GB | — | Won't run |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Coder 480B-A35B | Q2_K | 196 GB | — | Won't run |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | MiMo V2 Flash (309B-A15B) | Q2_K | 126 GB | — | Won't run |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Ling 1T | Q2_K | 405 GB | — | Won't run |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Large 3 (675B) | Q2_K | 273 GB | — | Won't run |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 235B-A22B Instruct 2507 | Q2_K | 97.7 GB | — | Won't run |
| 63Good quality (B) · 63 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Solar Open 2 250B | Q2_K | 104 GB | — | Won't run |
| 62Good quality (B) · 62 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Kimi K2 Instruct (July 2025) | Q2_K | 413 GB | — | Won't run |
| 62Good quality (B) · 62 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax M2 (230B-A10B) | Q2_K | 95.6 GB | — | Won't run |
| 62Good quality (B) · 62 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-VL 235B-A22B Instruct | Q2_K | 97.9 GB | — | Won't run |
| 61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Command A+ (218B-A25B) | Q2_K | 89.8 GB | — | Won't run |
| 61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | K-EXAONE 236B-A23B | Q2_K | 97.3 GB | — | Won't run |
| 61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | LongCat Flash Chat (560B) | Q2_K | 227 GB | — | Won't run |
| 61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3 Super 120B-A12B | Q2_K | 51.6 GB | — | Won't run |
| 61Good quality (B) · 61 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 235B-A22B | Q2_K | 97.6 GB | — | Won't run |
| 60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Devstral 2 (123B) | Q2_K | 55.0 GB | — | Won't run |
| 60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | InternVL3.5 241B-A28B | Q2_K | 99.9 GB | — | Won't run |
| 60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Laguna S 2.1 (118B-A8B) | Q2_K | 50.7 GB | — | Won't run |
| 60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.1 Nemotron Ultra 253B v1 | Q2_K | 108 GB | — | Won't run |
| 60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Coder Next (80B-A3B) | Q2_K | 34.1 GB | — | Won't run |
| 60Good quality (B) · 60 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-Next 80B-A3B Thinking | Q2_K | 34.8 GB | — | Won't run |
| 58Good quality (B) · 58 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Baichuan M3 235B-A22B | Q2_K | 97.7 GB | — | Won't run |
| 58Good quality (B) · 58 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4.6 (355B-A32B) | Q2_K | 148 GB | — | Won't run |
| 58Good quality (B) · 58 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Next 80B-A3B Instruct | Q2_K | 34.8 GB | — | Won't run |
| 58Good quality (B) · 58 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V3 0324 (671B) | Q2_K | 276 GB | — | Won't run |
| 58Good quality (B) · 58 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4.6V | Q2_K | 46.7 GB | — | Won't run |
| 58Good quality (B) · 58 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax-M1 80K | Q2_K | 185 GB | — | Won't run |
| 57Good quality (B) · 57 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Command A Reasoning (111B) | Q2_K | 47.2 GB | — | Won't run |
| 57Good quality (B) · 57 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4.5 (355B-A32B) | Q2_K | 148 GB | — | Won't run |
| 57Good quality (B) · 57 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Ling 3.0 Flash (127B-A5B) | Q2_K | 53.5 GB | — | Won't run |
| 57Good quality (B) · 57 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax-M1 40K | Q2_K | 185 GB | — | Won't run |
| 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Small 4 (119B-A6B) | Q2_K | 50.0 GB | — | Won't run |
| 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Medium 3.5 (128B) | Q2_K | 56.1 GB | — | Won't run |
| 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Trinity Large Thinking (400B-A13B) | Q2_K | 162 GB | — | Won't run |
| 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Command A (111B) | Q2_K | 47.2 GB | — | Won't run |
| 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE 4.5 300B-A47B | Q2_K | 124 GB | — | Won't run |
| 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4.5V | Q2_K | 46.7 GB | — | Won't run |
| 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Hermes 4 405B | Q2_K | 169 GB | — | Won't run |
| 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Kimi Dev 72B | Q2_K | 33.8 GB | — | Won't run |
| 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Ling 2.6 Flash (104B-A7.4B) | Q2_K | 45.1 GB | — | Won't run |
| 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.3 Nemotron Super 49B v1.5 | Q2_K | 24.7 GB | — | Won't run |
| 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Large 2.1 (2411) | Q2_K | 54.1 GB | — | Won't run |
| 56Good quality (B) · 56 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Solar Open 100B | Q2_K | 44.7 GB | — | Won't run |
| 54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4.5 Air (106B-A12B) | Q2_K | 47.8 GB | — | Won't run |
| 54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Large 2 (123B) | Q2_K | 54.2 GB | — | Won't run |
| 54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | NorthCUA Pro | Q2_K | 161 GB | — | Won't run |
| 54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Pixtral Large 124B (2411) | Q2_K | 54.6 GB | — | Won't run |
| 54Fair quality (C) · 54 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Ring Flash 2.0 (100B-A6B) | Q2_K | 43.8 GB | — | Won't run |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | dots.llm1 Instruct | Q2_K | 67.5 GB | — | Won't run |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Ling Flash 2.0 (100B-A6B) | Q2_K | 43.8 GB | — | Won't run |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax-Text-01 | Q2_K | 185 GB | — | Won't run |
| 53Fair quality (C) · 53 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Tülu 3 405B | Q2_K | 169 GB | — | Won't run |
| 52Fair quality (C) · 52 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V3 (671B) | Q2_K | 271 GB | — | Won't run |
| 52Fair quality (C) · 52 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Sarvam 105B | Q2_K | 44.8 GB | — | Won't run |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek Coder V2 (236B) | Q2_K | 96.9 GB | — | Won't run |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Hermes 4 70B | Q2_K | 33.0 GB | — | Won't run |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Hunyuan A13B (80B-A13B) | Q2_K | 35.3 GB | — | Won't run |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | InternVL3 78B | Q2_K | 36.1 GB | — | Won't run |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Leanstral 119B-A6B | Q2_K | 50.0 GB | — | Won't run |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.3 70B Instruct | Q2_K | 33.0 GB | — | Won't run |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 72B Instruct | Q2_K | 33.8 GB | — | Won't run |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-VL 72B Instruct | Q2_K | 34.1 GB | — | Won't run |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek Coder V2 Instruct (0614) | Q2_K | 96.9 GB | — | Won't run |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek R1 Distill Llama 70B | Q2_K | 33.0 GB | — | Won't run |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V2.5 1210 | Q2_K | 96.9 GB | — | Won't run |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.1 405B Instruct | Q2_K | 169 GB | — | Won't run |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Llama 4 Maverick (17B x 128E) | Q2_K | 164 GB | — | Won't run |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Llama 4 Scout 17B-16E | Q2_K | 47.1 GB | — | Won't run |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Tülu 3 70B | Q2_K | 33.0 GB | — | Won't run |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Command R+ (08-2024) 104B | Q2_K | 45.7 GB | — | Won't run |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V2.5 | Q2_K | 96.9 GB | — | Won't run |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Groot 65B A6B 261023 | Q2_K | 49.6 GB | — | Won't run |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Jamba 1.5 Large | Q2_K | 162 GB | — | Won't run |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.1 70B Instruct | Q2_K | 33.0 GB | — | Won't run |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Hermes 3 (Llama 3.1 70B) | Q2_K | 33.0 GB | — | Won't run |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Ling 3.0 flash Sante | Q2_K | 53.1 GB | — | Won't run |
| 47Fair quality (C) · 47 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | QVQ 72B Preview | Q2_K | 34.1 GB | — | Won't run |
| 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Apertus v1.5 70B | Q2_K | 33.5 GB | — | Won't run |
| 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.1 Nemotron 70B Instruct | Q2_K | 33.0 GB | — | Won't run |
| 46Fair quality (C) · 46 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.2 90B Vision Instruct | Q2_K | 40.9 GB | — | Won't run |
| 44Fair quality (C) · 44 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Command R+ 104B (04-2024) | Q2_K | 45.7 GB | — | Won't run |
| 44Fair quality (C) · 44 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2 72B Instruct | Q2_K | 33.8 GB | — | Won't run |
| 44Fair quality (C) · 44 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 6/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2-VL 72B Instruct | Q2_K | 34.1 GB | — | Won't run |
| 43Fair quality (C) · 43 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V2 Chat | Q2_K | 96.9 GB | — | Won't run |
| 42Fair quality (C) · 42 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | Apertus 70B Instruct | Q2_K | 33.0 GB | — | Won't run |
| 40Fair quality (C) · 40 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3 70B Instruct | Q2_K | 33.0 GB | — | Won't run |
| 40Fair quality (C) · 40 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-Math 72B Instruct | Q2_K | 32.5 GB | — | Won't run |
| 38Basic quality (D) · 38 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | Mixtral 8x22B Instruct | Q2_K | 60.2 GB | — | Won't run |
| 37Basic quality (D) · 37 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 5/100 (quality, fit, speed and memory use) sets the ranking. | Command R 35B (v01) | Q2_K | 26.8 GB | — | Won't run |
| 36Basic quality (D) · 36 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | Qwen1.5 110B Chat | Q2_K | 49.2 GB | — | Won't run |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | Aya 23 35B | Q2_K | 26.8 GB | — | Won't run |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | Grok-1 (314B) | Q2_K | 130 GB | — | Won't run |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | Jamba 1.5 Mini | Q2_K | 22.8 GB | — | Won't run |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2 57B-A14B Instruct | Q2_K | 25.5 GB | — | Won't run |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | Snowflake Arctic Instruct | Q2_K | 194 GB | — | Won't run |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 4/100 (quality, fit, speed and memory use) sets the ranking. | Code Llama 70B Instruct | Q2_K | 31.0 GB | — | Won't run |
| 28Basic quality (D) · 28 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek LLM 67B Chat | Q2_K | 30.6 GB | — | Won't run |
| 25Basic quality (D) · 25 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | Llama 2 70B Chat | Q2_K | 31.0 GB | — | Won't run |
| 23Basic quality (D) · 23 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 3/100 (quality, fit, speed and memory use) sets the ranking. | Falcon 180B Chat | Q2_K | 74.2 GB | — | Won't run |
Image models on the Intel Core Ultra 7 255H / 9 285H NAS (32 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | Z-Image Turbo | FP8 | 12.6 GB | 21 s | Runs well |
| 76Great quality (A) · 76 of 100: how capable the model is at FP8, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 4B | FP8 | 10.2 GB | 8.4 s | Runs great |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at FP8, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | FLUX 3 Image Klein | FP8 | 12.4 GB | 48 s | Slow |
| 83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE-Image Turbo | FP8 | 14.5 GB | 27 s | Runs well |
| 82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 9B | FP8 | 11.7 GB | 16 s | Runs wellencoder unloaded after use |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Krea 2 Turbo | FP8 | 15.7 GB | 38 s | Runs welltight fit · encoder unloaded after use |
| 80Great quality (A) · 80 of 100: how capable the model is at FP8, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Z-Image | FP8 | 12.6 GB | 2.4 min | Very slow |
| 81Great quality (A) · 81 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE-Image | Q4 GGUF | 15.1 GB | 4.1 min | Very slow |
| 65Good quality (B) · 65 of 100: how capable the model is at NF4, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.1 [schnell] | NF4 | 14.4 GB | 21 s | Runs well |
| 80Great quality (A) · 80 of 100: how capable the model is at FP8, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | MOSS-Image SFT | FP8 | 15.8 GB | 2.0 min | Slowtight fit |
| 60Good quality (B) · 60 of 100: how capable the model is at FP8, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Stable Diffusion 3.5 Large Turbo | FP8 | 16.3 GB | 13 s | Runs welltight fit |
| 74Great quality (A) · 74 of 100: how capable the model is at NF4, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.1 [dev] | NF4 | 14.4 GB | 2.1 min | Slow |
| 76Great quality (A) · 76 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.1 Kontext [dev] | Q4 GGUF | 15.5 GB | 4.1 min | Very slow |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at NF4, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Ideogram 4 | NF4 | 13.0 GB | 4.5 min | Very slowencoder unloaded after use |
| 76Great quality (A) · 76 of 100: how capable the model is at FP8, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Chroma1-HD | FP8 | 16.4 GB | 2.8 min | Very slowtight fit |
| 80Great quality (A) · 80 of 100: how capable the model is at FP8, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.1 Krea [dev] | FP8 | 14.7 GB | 1.8 min | Slowencoder unloaded after use |
| 54Fair quality (C) · 54 of 100: how capable the model is at FP16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | SDXL-Lightning (4-step) | FP16 | 8.9 GB | 6.5 s | Runs great |
| 50Fair quality (C) · 50 of 100: how capable the model is at FP16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | PixArt-Σ XL 1024 | FP16 | 12.8 GB | 14 s | Runs well |
| 72Great quality (A) · 72 of 100: how capable the model is at FP16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Iris-3B | FP16 | 17.3 GB | 2.5 min | Very slowtight fit |
| 62Good quality (B) · 62 of 100: how capable the model is at FP16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Lumina-Image 2.0 | FP16 | 12.7 GB | 65 s | Slow |
| 58Good quality (B) · 58 of 100: how capable the model is at FP8, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Kolors | FP8 | 11.0 GB | 34 s | Runs well |
| 74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.1 Fill [dev] | FP8 | 14.7 GB | 1.8 min | Slowencoder unloaded after use |
| 78Great quality (A) · 78 of 100: how capable the model is at NF4, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | HiDream-I1 Full | NF4 | 12.6 GB | 8.1 min | Very slowencoder unloaded after use |
| 64Good quality (B) · 64 of 100: how capable the model is at FP8, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Stable Diffusion 3.5 Large | FP8 | 16.3 GB | 1.5 min | Slowtight fit |
| 74Great quality (A) · 74 of 100: how capable the model is at NF4, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | HiDream-I1 Dev | NF4 | 12.6 GB | 3.1 min | Very slowencoder unloaded after use |
| 56Good quality (B) · 56 of 100: how capable the model is at FP8, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | DreamShaper XL v2 Turbo | FP8 | 5.6 GB | 11 s | Runs great |
| 70Great quality (A) · 70 of 100: how capable the model is at NF4, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | HiDream-I1 Fast | NF4 | 12.6 GB | 1.8 min | Slowencoder unloaded after use |
| 64Good quality (B) · 64 of 100: how capable the model is at FP8, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | OmniGen2 | FP8 | 10.3 GB | 2.2 min | Very slow |
| 80Great quality (A) · 80 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | FireRed-Image-Edit 1.1 | Q4 GGUF | 16.0 GB | 15.7 min | Very slowtight fit · encoder unloaded after use |
| 60Good quality (B) · 60 of 100: how capable the model is at FP16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Animagine XL 4.0 | FP16 | 8.9 GB | 39 s | Runs well |
| 60Good quality (B) · 60 of 100: how capable the model is at FP16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Illustrious XL v0.1 | FP16 | 8.9 GB | 39 s | Runs well |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at FP8, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax H3 Image | FP8 | 16.0 GB | 1.8 min | Slowtight fit · CPU offload |
| 79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image-Edit 2511 | Q4 GGUF | 16.0 GB | 15.7 min | Very slowtight fit · encoder unloaded after use |
| 58Good quality (B) · 58 of 100: how capable the model is at FP16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Pony Diffusion V6 XL | FP16 | 8.9 GB | 35 s | Runs well |
| 56Good quality (B) · 56 of 100: how capable the model is at FP8, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Stable Diffusion 3.5 Medium | FP8 | 10.4 GB | 50 s | Slow |
| 52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Stable Cascade | FP16 | 14.0 GB | 47 s | Slow |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [dev] | Q8 GGUF | 15.4 GB | 8.4 min | Very slowCPU offload |
| 70Great quality (A) · 70 of 100: how capable the model is at FP16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | CogView4 6B | FP16 | 15.1 GB | 2.9 min | Very slowencoder unloaded after use |
| 50Fair quality (C) · 50 of 100: how capable the model is at FP8, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Stable Diffusion 3 Medium | FP8 | 9.9 GB | 26 s | Runs well |
| 56Good quality (B) · 56 of 100: how capable the model is at FP16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Animagine XL 3.1 | FP16 | 8.9 GB | 39 s | Runs well |
| 60Good quality (B) · 60 of 100: how capable the model is at FP16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Playground v2.5 | FP16 | 8.9 GB | 70 s | Slow |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at FP8, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image 2.1 Turbo | FP8 | 16.7 GB | 2.1 min | Slowtight fit · CPU offload |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image 2512 | Q8 GGUF | 13.8 GB | 20.9 min | Very slowCPU offload |
| 56Good quality (B) · 56 of 100: how capable the model is at FP8, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | AuraFlow v0.3 | FP8 | 10.4 GB | 2.0 min | Slow |
| 40Fair quality (C) · 40 of 100: how capable the model is at FP16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | SDXL Turbo | FP16 | 7.6 GB | 1.4 s | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at FP8, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image | FP8 | 13.3 GB | 16.4 min | Very slowCPU offload |
| 60Good quality (B) · 60 of 100: how capable the model is at FP8, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Juggernaut XL v9 | FP8 | 5.6 GB | 38 s | Runs well |
| 60Good quality (B) · 60 of 100: how capable the model is at FP8, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | RealVisXL V5.0 | FP8 | 5.6 GB | 38 s | Runs well |
| 93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Fibo 2.0 Dev | FP16 | 8.1 GB | 4.6 min | Very slowCPU offload |
| 84Great quality (A) · 84 of 100: how capable the model is at FP8, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Ming-Image 0.1 Design | FP8 | 16.4 GB | 3.0 min | Very slowtight fit · CPU offload |
| 52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Hunyuan-DiT v1.2 | FP16 | 9.3 GB | 56 s | Slow |
| 53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Stable Diffusion XL 1.0 | FP8 | 5.6 GB | 38 s | Runs well |
| 42Fair quality (C) · 42 of 100: how capable the model is at FP16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Realistic Vision V5.1 | FP16 | 2.8 GB | 11 s | Runs great |
| 40Fair quality (C) · 40 of 100: how capable the model is at FP16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | DreamShaper 8 | FP16 | 2.8 GB | 11 s | Runs great |
| 35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Stable Diffusion 1.5 | FP16 | 2.8 GB | 11 s | Runs great |
| 48Fair quality (C) · 48 of 100: how capable the model is at FP16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Kandinsky 3 | FP16 | 8.7 GB | 88 s | Slowencoder unloaded after use |
| 30Basic quality (D) · 30 of 100: how capable the model is at FP16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | LCM DreamShaper v7 | FP16 | 2.8 GB | 2.3 s | Runs great |
| 28Basic quality (D) · 28 of 100: how capable the model is at FP16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | SD Turbo | FP16 | 3.3 GB | 0.7 s | Runs great |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 12/100 (quality, fit, speed and memory use) sets the ranking. | Cosmos3-Super Text2Image (64B) | FP8 | 26.1 GB | — | Won't run |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at FP8, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | HunyuanImage 3.0 (80B-A13B) | FP8 | 32.8 GB | — | Won't run |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image 2.1 | Q4 GGUF | 26.0 GB | — | Won't run |
Video models on the Intel Core Ultra 7 255H / 9 285H NAS (32 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 49Fair quality (C) · 49 of 100: how capable the model is at FP8, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | LTX-Video 2B | FP8 | 10.8 GB | 3.5 min | Runs great |
| 74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | HY-OmniWeaving (8.3B, unified video) | FP8 | 15.7 GB | 77.9 min | Very slowtight fit · encoder unloaded after use |
| 53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | CogVideoX 5B | FP8 | 14.3 GB | 25.2 min | Slow |
| 53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | CogVideoX 5B I2V | FP8 | 14.9 GB | 25.2 min | Slow |
| 68Good quality (B) · 68 of 100: how capable the model is at FP16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Kandinsky 6.0 Video Lite (3B, video + audio) | FP16 | 14.7 GB | 50.6 min | Very slowencoder unloaded after use |
| 53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.1 T2V 1.3B | FP8 | 12.8 GB | 33.6 min | Slow |
| 53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.1 VACE 1.3B | FP8 | 13.7 GB | 36.4 min | Slow |
| 68Good quality (B) · 68 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.1 I2V 14B 480P | Q4 GGUF | 14.2 GB | 2.9 h | Very slowencoder unloaded after use |
| 44Fair quality (C) · 44 of 100: how capable the model is at FP8, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | CogVideoX 2B | FP8 | 11.0 GB | 8.4 min | Runs well |
| 81Great quality (A) · 81 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.5 (22B, video + audio) | Q4 GGUF | 16.8 GB | 22.1 min | Slowtight fit · CPU offload |
| 70Great quality (A) · 70 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.2 S2V 14B (speech to video) | Q4 GGUF | 15.6 GB | 3.3 h | Very slowtight fit · encoder unloaded after use |
| 83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Bernini-R A14B (video generation + editing) | FP8 | 10.7 GB | 2.2 h | Very slowCPU offload |
| 50Fair quality (C) · 50 of 100: how capable the model is at FP8, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | SkyReels V2 Diffusion Forcing 1.3B | FP8 | 16.7 GB | 42.0 min | Very slowtight fit |
| 78Great quality (A) · 78 of 100: how capable the model is at FP8, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | SCAIL-2 14B (character animation) | FP8 | 12.5 GB | 3.6 h | Very slowCPU offload |
| 79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.3 | Q4 GGUF | 16.4 GB | 1.6 h | Very slowtight fit · CPU offload |
| 74Great quality (A) · 74 of 100: how capable the model is at FP16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | FramePack I2V (HunyuanVideo 13B) | FP16 | 15.3 GB | 80.9 min | Very slowCPU offload |
| 66Good quality (B) · 66 of 100: how capable the model is at FP8, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | LTX-Video 13B 0.9.8 (distilled) | FP8 | 16.1 GB | 10.9 min | Runs welltight fit · CPU offload |
| 76Great quality (A) · 76 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2 (19B, video + audio) | Q4 GGUF | 16.4 GB | 1.6 h | Very slowtight fit · CPU offload |
| 35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | AnimateDiff v3 (SD 1.5) | FP16 | 4.7 GB | 3.1 min | Runs great |
| 72Great quality (A) · 72 of 100: how capable the model is at FP8, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | SkyReels V2 T2V 14B 540P | FP8 | 14.2 GB | 4.2 h | Very slowCPU offload |
| 60Good quality (B) · 60 of 100: how capable the model is at FP8, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Mochi 1 Preview (10B) | FP8 | 14.7 GB | 3.3 h | Very slowCPU offload |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | Cosmos3-Super Image2Video (64B) | FP16 | 53.7 GB | — | Won't run |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | Kandinsky 6.0 Pro (29B, video + audio) | FP16 | 27.8 GB | — | Won't run |
| 83Great quality (A) · 83 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax H3 (33B, video + audio) | Q4 GGUF | 19.6 GB | — | Won't run |
| 82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | HunyuanVideo 1.5 (8.3B) | FP8 | 23.9 GB | — | Won't run |
| 79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.2 I2V A14B | Q4 GGUF | 21.3 GB | — | Won't run |
| 79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.2 T2V A14B | Q4 GGUF | 21.3 GB | — | Won't run |
| 76Great quality (A) · 76 of 100: how capable the model is at FP8, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | SkyReels V2 T2V 14B 720P | FP8 | 26.0 GB | — | Won't run |
| 74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | Step-Video T2V (30B) | FP8 | 25.0 GB | — | Won't run |
| 74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | Wan-Dancer 14B (music to dance) | FP8 | 35.6 GB | — | Won't run |
| 72Great quality (A) · 72 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.1 I2V 14B 720P | Q4 GGUF | 21.3 GB | — | Won't run |
| 72Great quality (A) · 72 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.1 T2V 14B | Q4 GGUF | 21.3 GB | — | Won't run |
| 72Great quality (A) · 72 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.1 VACE 14B | Q4 GGUF | 22.0 GB | — | Won't run |
| 72Great quality (A) · 72 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.2 Animate 14B | Q4 GGUF | 21.3 GB | — | Won't run |
| 70Great quality (A) · 70 of 100: how capable the model is at FP16, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | Open-Sora 2.0 (11B) | FP16 | 19.3 GB | — | Won't run |
| 68Good quality (B) · 68 of 100: how capable the model is at FP8, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | Cosmos-Predict2 14B Video2World | FP8 | 24.7 GB | — | Won't run |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | HunyuanVideo 13B | Q4 GGUF | 24.8 GB | — | Won't run |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | HunyuanVideo I2V 13B | Q4 GGUF | 24.8 GB | — | Won't run |
| 65Good quality (B) · 65 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.2 TI2V 5B | Q4 GGUF | 21.4 GB | — | Won't run |
| 60Good quality (B) · 60 of 100: how capable the model is at FP16, whatever it runs on. Match score 8/100 (quality, fit, speed and memory use) sets the ranking. | Cosmos 1.0 Diffusion 7B Text2World | FP16 | 29.2 GB | — | Won't run |
| 58Good quality (B) · 58 of 100: how capable the model is at FP8, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | CogVideoX 1.5 5B | FP8 | 31.2 GB | — | Won't run |
| 56Good quality (B) · 56 of 100: how capable the model is at FP8, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Cosmos-Predict2 2B Video2World | FP8 | 20.5 GB | — | Won't run |
| 52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 7/100 (quality, fit, speed and memory use) sets the ranking. | Allegro (2.8B) | FP16 | 24.7 GB | — | Won't run |
Decision models on the Intel Core Ultra 7 255H / 9 285H NAS (32 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3.5 | F16 | 3.5 GB | 73 ms | Runs great |
| 84Great quality (A) · 84 of 100: how capable the model is at F16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3 | F16 | 3.5 GB | 73 ms | Runs great |
| 80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | FRIDA-Decisions | F16 | 2.4 GB | 45 ms | Runs great |
| 80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | GLiNER2.5 Decide | F16 | 1.7 GB | 28 ms | Runs great |
| 80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 0.6B | F16 | 3.5 GB | 73 ms | Runs great |
| 76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | Llama Prompt Guard 2 86M | F16 | 1.2 GB | 32 ms | Runs great |
| 76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | mxbai-rerank-base v2 | F16 | 3.1 GB | 60 ms | Runs great |
| 82Great quality (A) · 82 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | mxbai-rerank-large v2 | Q8_0 | 3.8 GB | 151 ms | Runs well |
| 74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | GLiClass ModernBERT Large v3 | F16 | 1.5 GB | 24 ms | Runs great |
| 81Great quality (A) · 81 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | d1 3B | Q6_K | 4.7 GB | 165 ms | Runs well |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 4B | Q8_0 | 6.6 GB | 388 ms | Runs well |
| 78Great quality (A) · 78 of 100: how capable the model is at F16, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | OpenAI Privacy Filter | F16 | 3.8 GB | 6.5 ms | Runs great |
| 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | zerank-1 small | Q8_0 | 4.1 GB | 168 ms | Runs well |
| 72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | BGE Reranker v2 M3 | F16 | 1.9 GB | 61 ms | Runs great |
| 72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | DeBERTa v3 Large Zero-shot v2.0 | F16 | 1.6 GB | 26 ms | Runs great |
| 72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | DuoGuard 0.5B | F16 | 1.7 GB | 53 ms | Runs great |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | zerank-2 | Q8_0 | 6.6 GB | 388 ms | Runs well |
| 84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | Intern-Decision 4B | Q8_0 | 6.9 GB | 257 ms | Runs well |
| 72Great quality (A) · 72 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | Skywork Reward V2 Qwen3 0.6B | Q8_0 | 1.4 GB | 108 ms | Runs great |
| 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | LemonDecider 4B | Q8_0 | 6.5 GB | 200 ms | Runs well |
| 70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | GTE Reranker ModernBERT Base | F16 | 0.9 GB | 19 ms | Runs great |
| 70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v2 Base Multilingual | F16 | 1.2 GB | 32 ms | Runs great |
| 70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | ModernBERT Large Zero-shot v2.0 | F16 | 1.5 GB | 24 ms | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | Shieldstral 1.0 3B | Q8_0 | 6.4 GB | 372 ms | Runs well |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 8B | Q8_0 | 11.0 GB | 787 ms | Slow |
| 68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | GLiGuard 300M | F16 | 1.1 GB | 25 ms | Runs great |
| 68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | Granite Embedding Reranker English R2 | F16 | 0.9 GB | 19 ms | Runs great |
| 68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | Laya | F16 | 1.5 GB | 25 ms | Runs great |
| 68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | Llama Prompt Guard 2 22M | F16 | 0.8 GB | 11 ms | Runs great |
| 78Great quality (A) · 78 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | BGE Reranker v2 Gemma | Q8_0 | 4.8 GB | 244 ms | Runs well |
| 66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | GLiClass Base v3 | F16 | 1.0 GB | 13 ms | Runs great |
| 66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | ProtectAI DeBERTa v3 Prompt Injection v2 | F16 | 1.0 GB | 22 ms | Runs great |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Skywork Reward V2 Llama 3.1 8B | Q8_0 | 10.4 GB | 1.3 s | Slow |
| 73Great quality (A) · 73 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3Guard Gen 0.6B | Q6_K | 2.9 GB | 117 ms | Runs great |
| 64Good quality (B) · 64 of 100: how capable the model is at F16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | DeBERTa v3 Base Zero-shot v2.0 | F16 | 1.0 GB | 13 ms | Runs great |
| 68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | GLiNER2 Base v1 | F16 | 1.1 GB | 14 ms | Runs great |
| 62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | HHEM 2.1 Open | F16 | 0.8 GB | 26 ms | Runs great |
| 66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | LettuceDetect Large | F16 | 1.5 GB | 84 ms | Runs great |
| 60Good quality (B) · 60 of 100: how capable the model is at F16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Laya Multilingual | F16 | 1.3 GB | 20 ms | Runs great |
| 84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Skywork Reward V2 Qwen3 8B | Q8_0 | 10.5 GB | 1.3 s | Slow |
| 62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | GLiNER Multi v2.1 | F16 | 1.3 GB | 18 ms | Runs great |
| 83Great quality (A) · 83 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3Guard Gen 4B | Q6_K | 6.0 GB | 667 ms | Slow |
| 56Good quality (B) · 56 of 100: how capable the model is at F16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | BART Large MNLI | F16 | 1.5 GB | 24 ms | Runs great |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3Guard Gen 8B | Q6_K | 9.1 GB | 1.2 s | Slow |
| 83Great quality (A) · 83 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.1 Nemotron Safety Guard 8B v3 | Q6_K | 8.9 GB | 1.2 s | Slow |
| 83Great quality (A) · 83 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Granite Guardian 4.1 8B | Q6_K | 9.3 GB | 1.3 s | Slow |
| 52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | ms-marco MiniLM L6 v2 | F16 | 0.7 GB | 6.3 ms | Runs great |
| 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | WildGuard 7B | Q8_0 | 10.0 GB | 1.3 s | Slow |
| 79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Granite Guardian 3.3 8B | Q6_K | 9.1 GB | 1.2 s | Slow |
| 75Great quality (A) · 75 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | NuExtract 2.0 4B | Q6_K | 5.2 GB | 1.2 s | Slow |
| 58Good quality (B) · 58 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | ShieldGemma 2B | Q8_0 | 5.0 GB | 253 ms | Runs well |
| 69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | NuExtract 2.0 2B | Q6_K | 3.9 GB | 717 ms | Slow |
| 64Good quality (B) · 64 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | ShieldGemma 9B | Q8_0 | 12.6 GB | 887 ms | Slow |
| 55Good quality (B) · 55 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Llama Guard 3 1B | Q6_K | 3.4 GB | 229 ms | Runs well |
| 67Good quality (B) · 67 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Llama Guard 3 8B | Q6_K | 8.9 GB | 1.2 s | Slow |
| 79Great quality (A) · 79 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | DynaGuard 8B | Q8_0 | 11.0 GB | 21.7 s | Very slow |
| 78Great quality (A) · 78 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron Content Safety Reasoning 4B | Q8_0 | 6.9 GB | 11.4 s | Very slow |
| 76Great quality (A) · 76 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | gpt-oss-safeguard 20B | MXFP4 | 14.4 GB | 5.2 s | Very slow |
| 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Selene 1 Mini 8B | Q8_0 | 10.8 GB | 20.6 s | Very slow |
| 78Great quality (A) · 78 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | CompassJudger-2 7B | Q8_0 | 10.3 GB | 19.6 s | Very slow |
| 66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Llama Guard 4 12B | Q8_0 | 15.2 GB | 2.1 s | Very slow |
| 69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | DynaGuard 1.7B | Q6_K | 4.0 GB | 4.0 s | Very slow |
| 68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Prometheus 2 7B | Q8_0 | 10.0 GB | 18.6 s | Very slow |
| 66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | GLIDER | Q8_0 | 6.9 GB | 9.8 s | Very slow |
| 64Good quality (B) · 64 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Flow Judge v0.1 | Q8_0 | 6.9 GB | 9.8 s | Very slow |
| 62Good quality (B) · 62 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | ShieldGemma 27B | Q4_K_M | 19.4 GB | 2.4 s | Very slowover GPU memory limit |
| 81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | CompassJudger-2 32B | Q4_K_M | 22.6 GB | 52.5 s | Very slowfar over GPU memory limit |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 11/100 (quality, fit, speed and memory use) sets the ranking. | GLiDE 27B | Q8_0 | 34.8 GB | — | Won't run |
| 80Great quality (A) · 80 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. | gpt-oss-safeguard 120B | MXFP4 | 68.7 GB | — | Won't run |
| 70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 9/100 (quality, fit, speed and memory use) sets the ranking. | Prometheus 2 8x7B | Q4_K_M | 30.8 GB | — | Won't run |
Upgrade picks
GPUs that would run more LLMs without offloading, at launch prices. Right now 386 of 622 LLMs run well on your Intel Core Ultra 7 255H / 9 285H NAS (32 GB).
Biggest jump
NVIDIA RTX PRO 6000 Blackwell
+161 LLMs run well, including Qwen3.8 Flash Next (125B-A6B)
Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.