NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip spec sheet
What the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip 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.
- VRAM
- 252 GB
- Usable for models
- 252 GB
- Memory bandwidth
- 7,100 GB/s
- FP16 compute
- 80.0 TFLOPS
Open in Model Finder Best LLMs by task Compare with another GPU
LLMs on the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 96Excellent quality (A+) · 96 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 98/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.8 Flash Next (125B-A6B) | Q8_0 | 204 GB | 194 tok/s | Runs great |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax M2.7 (230B-A10B) | Q6_K | 203 GB | 190 tok/s | Runs great |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. | Step 3.7 Flash (198B-A11B) | Q6_K | 179 GB | 184 tok/s | Runs great |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at F16, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3.5 Bolt 74B-A9B | F16 | 163 GB | 114 tok/s | Runs great |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. | Nex N2.6 (321B-A18B) | Q4_K_M | 209 GB | 184 tok/s | Runs great |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. | GLM-5.3 Flash (320B-A18B) | Q4_K_M | 209 GB | 184 tok/s | Runs great |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. | MiMo V2.6 Flash (310B-A15B) | Q4_K_M | 203 GB | 197 tok/s | Runs great |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax M2.5 (230B-A10B) | Q6_K | 203 GB | 190 tok/s | Runs great |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | Step 3.5 Flash (196B-A11B) | Q6_K | 177 GB | 184 tok/s | Runs great |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at F16, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | Kolibri 1 (78B-A3.5B) | F16 | 170 GB | 165 tok/s | Runs great |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | Inkling Small (276B-A12B) | Q5_K_M | 202 GB | 194 tok/s | Runs great |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | Naive N0.5 Flash (309B-A15.5B) | Q4_K_M | 202 GB | 194 tok/s | Runs great |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax M2.1 (230B-A10B) | Q6_K | 203 GB | 190 tok/s | Runs great |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 235B-A22B Thinking 2507 | Q6_K | 208 GB | 138 tok/s | Runs great |
| 93Excellent quality (A+) · 93 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3.5 Super VL 120B-A12B | Q8_0 | 145 GB | 154 tok/s | Runs great |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | Hunyuan Hy3 (295B-A21B) | Q4_K_M | 198 GB | 173 tok/s | Runs great |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V4 Flash (284B-A13B) | Q4_K_M | 199 GB | 206 tok/s | Runs great |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | MiMo V2.5 (310B-A15B) | Q4_K_M | 203 GB | 197 tok/s | Runs great |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.5 122B-A10B | Q8_0 | 146 GB | 165 tok/s | Runs great |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 235B-A22B Instruct 2507 | Q6_K | 208 GB | 138 tok/s | Runs great |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 122B-A10B | Q8_0 | 146 GB | 165 tok/s | Runs great |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax M2 (230B-A10B) | Q6_K | 203 GB | 190 tok/s | Runs great |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-VL 235B-A22B Instruct | Q6_K | 208 GB | 138 tok/s | Runs great |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. | K2-Horizon (375B-A23B) | Q4_K_M | 247 GB | 167 tok/s | Runs welltight fit |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V4 Flash (April 2026) | Q4_K_M | 191 GB | 206 tok/s | Runs great |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. | Solar Open 2 250B | Q5_K_M | 193 GB | 179 tok/s | Runs great |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. | Command A+ (218B-A25B) | Q6_K | 193 GB | 129 tok/s | Runs great |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. | K-EXAONE 236B-A23B | Q6_K | 208 GB | 135 tok/s | Runs great |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 235B-A22B | Q6_K | 207 GB | 138 tok/s | Runs great |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4.7 (355B-A32B) | Q4_K_M | 235 GB | 142 tok/s | Runs welltight fit |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | MiMo V2 Flash (309B-A15B) | Q4_K_M | 202 GB | 197 tok/s | Runs great |
| 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. | Qwen3 Coder Next (80B-A3B) | F16 | 173 GB | 171 tok/s | Runs great |
| 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. | Qwen3-Next 80B-A3B Thinking | F16 | 176 GB | 171 tok/s | Runs great |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | InternVL3.5 241B-A28B | Q6_K | 212 GB | 121 tok/s | Runs great |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3 Super 120B-A12B | Q8_0 | 144 GB | 154 tok/s | 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. | Qwen3 Next 80B-A3B Instruct | F16 | 176 GB | 171 tok/s | Runs great |
| 83Great quality (A) · 83 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Baichuan M3 235B-A22B | Q6_K | 208 GB | 138 tok/s | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | Laguna S 2.1 (118B-A8B) | Q8_0 | 139 GB | 178 tok/s | Runs great |
| 80Great quality (A) · 80 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | Intern-S2 (397B-A17B) | Q3_K_M | 211 GB | 211 tok/s | Runs great |
| 79Great quality (A) · 79 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | Nex N2 Pro (397B-A17B) | Q3_K_M | 208 GB | 211 tok/s | Runs great |
| 79Great quality (A) · 79 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 397B-A17B | Q3_K_M | 211 GB | 211 tok/s | Runs great |
| 81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.1 Nemotron Ultra 253B v1 | Q4_K_M | 172 GB | 34.4 tok/s | Runs great |
| 81Great quality (A) · 81 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax M3.1 Flash (428B-A23B) | Q3_K_M | 224 GB | 189 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 90/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.5 397B-A17B | Q3_K_M | 211 GB | 211 tok/s | Runs great |
| 82Great quality (A) · 82 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | Ling 3.0 Flash (127B-A5B) | Q8_0 | 149 GB | 202 tok/s | Runs great |
| 95Excellent quality (A+) · 95 of 100: how capable the model is at F16, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | Nanbeige4.3 33B | F16 | 81.2 GB | 61.7 tok/s | Runs great |
| 79Great quality (A) · 79 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4.6 (355B-A32B) | Q4_K_M | 234 GB | 142 tok/s | Runs welltight fit |
| 93Excellent quality (A+) · 93 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. | Qwen3.6 35B-A3B | F16 | 85.3 GB | 171 tok/s | Runs great |
| 79Great quality (A) · 79 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax M3 (427B) | Q3_K_M | 223 GB | 183 tok/s | Runs welltight fit |
| 93Excellent quality (A+) · 93 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. | Qwen3.5 35B-A3B | F16 | 85.3 GB | 171 tok/s | Runs great |
| 93Excellent quality (A+) · 93 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. | MiniCPM-V 4.7 35B-A3B | F16 | 83.8 GB | 171 tok/s | Runs great |
| 95Excellent quality (A+) · 95 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. | Qwen3.8 27B | F16 | 69.3 GB | 73.6 tok/s | Runs great |
| 76Great quality (A) · 76 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. | dots.llm1 Instruct | Q8_0 | 173 GB | 144 tok/s | Runs great |
| 76Great quality (A) · 76 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE 4.5 300B-A47B | Q4_K_M | 198 GB | 114 tok/s | Runs great |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | Devstral 2 (123B) | Q6_K | 119 GB | 48.4 tok/s | Runs great |
| 83Great quality (A) · 83 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. | GLM-4.6V | Q8_0 | 129 GB | 154 tok/s | Runs great |
| 80Great quality (A) · 80 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. | Mistral Small 4 (119B-A6B) | Q8_0 | 140 GB | 194 tok/s | Runs great |
| 77Great quality (A) · 77 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4.5 (355B-A32B) | Q4_K_M | 235 GB | 142 tok/s | Runs welltight fit |
| 92Excellent quality (A+) · 92 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. | Nex N2 Mini (35B-A3B) | F16 | 83.6 GB | 171 tok/s | Runs great |
| 90Excellent quality (A+) · 90 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. | Flint (40B-A2.5B) | F16 | 93.0 GB | 179 tok/s | Runs great |
| 82Great quality (A) · 82 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. | Command A Reasoning (111B) | Q8_0 | 132 GB | 39.9 tok/s | Runs great |
| 91Excellent quality (A+) · 91 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. | Sage-A1.5 35B-A3B | F16 | 85.3 GB | 171 tok/s | Runs great |
| 94Excellent quality (A+) · 94 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. | Qwen3.6 27B | F16 | 69.3 GB | 73.6 tok/s | Runs great |
| 91Excellent quality (A+) · 91 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. | KAT-Coder V2.5 Dev (35B-A3B) | F16 | 82.7 GB | 171 tok/s | Runs great |
| 76Great quality (A) · 76 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Coder 480B-A35B | Q3_K_M | 251 GB | 158 tok/s | Runs welltight fit |
| 90Excellent quality (A+) · 90 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. | Ornith 1.5 35B-A3B | F16 | 85.3 GB | 171 tok/s | Runs great |
| 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. | Hunyuan A13B (80B-A13B) | F16 | 175 GB | 93.2 tok/s | Runs great |
| 93Excellent quality (A+) · 93 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. | Qwen3.5 27B | F16 | 69.3 GB | 73.6 tok/s | Runs great |
| 92Excellent quality (A+) · 92 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. | Muse Glimmer 30B | F16 | 72.9 GB | 68.7 tok/s | Runs great |
| 80Great quality (A) · 80 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. | Command A (111B) | Q8_0 | 132 GB | 39.9 tok/s | Runs great |
| 91Excellent quality (A+) · 91 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. | Gemma 4 31B | F16 | 77.4 GB | 65.4 tok/s | Runs great |
| 73Great quality (A) · 73 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek Coder V2 (236B) | Q6_K | 207 GB | 141 tok/s | Runs great |
| 89Excellent quality (A+) · 89 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. | Apodex 1.1 Mini (35B-A3B) | F16 | 85.3 GB | 171 tok/s | Runs great |
| 89Excellent quality (A+) · 89 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. | Ornith 1.0 35B-A3B | F16 | 85.3 GB | 171 tok/s | 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. | GLM-4.5V | Q8_0 | 129 GB | 154 tok/s | 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. | Ling 2.6 Flash (104B-A7.4B) | Q8_0 | 127 GB | 183 tok/s | Runs great |
| 92Excellent quality (A+) · 92 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. | Gemma 4 26B-A4B | F16 | 65.2 GB | 160 tok/s | 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. | Solar Open 100B | Q8_0 | 124 GB | 154 tok/s | Runs great |
| 78Great quality (A) · 78 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. | GLM-4.5 Air (106B-A12B) | Q8_0 | 132 GB | 154 tok/s | Runs great |
| 71Great quality (A) · 71 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek Coder V2 Instruct (0614) | Q6_K | 207 GB | 141 tok/s | Runs great |
| 71Great quality (A) · 71 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V2.5 1210 | Q6_K | 207 GB | 141 tok/s | Runs great |
| 79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Medium 3.5 (128B) | Q6_K | 121 GB | 47.4 tok/s | Runs great |
| 87Excellent quality (A+) · 87 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. | Agents-A1 35B-A3B | F16 | 83.6 GB | 171 tok/s | Runs great |
| 90Excellent quality (A+) · 90 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. | TMax 27B | F16 | 68.5 GB | 74.7 tok/s | Runs great |
| 87Excellent quality (A+) · 87 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. | Qwen AgentWorld 35B-A3B | F16 | 82.7 GB | 171 tok/s | Runs great |
| 80Great quality (A) · 80 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. | Llama 3.3 Nemotron Super 49B v1.5 | F16 | 116 GB | 41.0 tok/s | Runs great |
| 88Excellent quality (A+) · 88 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. | GLM-4.7 Flash (30B-A3B) | F16 | 76.1 GB | 171 tok/s | Runs great |
| 78Great quality (A) · 78 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. | Ring Flash 2.0 (100B-A6B) | Q8_0 | 123 GB | 193 tok/s | Runs great |
| 79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Large 2.1 (2411) | Q6_K | 117 GB | 49.3 tok/s | Runs great |
| 69Good quality (B) · 69 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V2.5 | Q6_K | 207 GB | 141 tok/s | Runs great |
| 74Great quality (A) · 74 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. | Leanstral 119B-A6B | Q8_0 | 140 GB | 190 tok/s | Runs great |
| 88Excellent quality (A+) · 88 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. | Raon-1 mini Preview (30B-A4B) | F16 | 70.8 GB | 154 tok/s | Runs great |
| 88Excellent quality (A+) · 88 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. | Fara 1.5 27B | F16 | 68.5 GB | 74.7 tok/s | Runs great |
| 77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | Pixtral Large 124B (2411) | Q6_K | 118 GB | 48.8 tok/s | Runs great |
| 77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Large 2 (123B) | Q6_K | 117 GB | 49.2 tok/s | Runs great |
| 76Great quality (A) · 76 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. | Ling Flash 2.0 (100B-A6B) | Q8_0 | 123 GB | 193 tok/s | Runs great |
| 69Good quality (B) · 69 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. | MiniMax-M1 80K | Q3_K_M | 237 GB | 137 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 85/100 (quality, fit, speed and memory use) sets the ranking. | Trinity Large Thinking (400B-A13B) | Q3_K_M | 209 GB | 228 tok/s | Runs great |
| 75Great quality (A) · 75 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. | Sarvam 105B | Q8_0 | 126 GB | 165 tok/s | Runs great |
| 84Great quality (A) · 84 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | gpt-oss 120B | MXFP4 | 80.1 GB | 256 tok/s | Runs great |
| 85Excellent quality (A+) · 85 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. | Hunyuan Hy-Memory 30B-A3B | F16 | 74.1 GB | 171 tok/s | Runs great |
| 68Good quality (B) · 68 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. | MiniMax-M1 40K | Q3_K_M | 237 GB | 137 tok/s | Runs welltight fit |
| 86Excellent quality (A+) · 86 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. | UI-Mate 27B | F16 | 68.5 GB | 74.7 tok/s | Runs great |
| 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Beam 1.0 (501B-A23B) | Q2_K | 214 GB | 210 tok/s | Runs great |
| 68Good quality (B) · 68 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Ling 3.1 Flash 1019 (560B-A25B) | Q2_K | 242 GB | 205 tok/s | Runs welltight fit |
| 80Great quality (A) · 80 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. | Kimi Dev 72B | Q8_0 | 93.0 GB | 61.0 tok/s | Runs great |
| 65Good quality (B) · 65 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. | NorthCUA Pro | Q3_K_M | 208 GB | 211 tok/s | Runs great |
| 82Great quality (A) · 82 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. | EXAONE 4.5 33B | F16 | 82.6 GB | 59.5 tok/s | Runs great |
| 82Great quality (A) · 82 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. | Laguna XS 2.1 (33B-A3B) | F16 | 81.4 GB | 171 tok/s | Runs great |
| 72Great quality (A) · 72 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. | Llama 4 Scout 17B-16E | Q8_0 | 130 GB | 131 tok/s | Runs great |
| 70Great quality (A) · 70 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. | Groot 65B A6B 261023 | Q8_0 | 139 GB | 194 tok/s | Runs great |
| 68Good quality (B) · 68 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. | Ling 3.0 flash Sante | Q8_0 | 148 GB | 202 tok/s | Runs great |
| 66Good quality (B) · 66 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Ling 3.1 Flash (560B-A25B) | Q2_K | 242 GB | 205 tok/s | Runs welltight fit |
| 80Great quality (A) · 80 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. | Seed-OSS 36B Instruct | F16 | 87.6 GB | 56.6 tok/s | Runs great |
| 79Great quality (A) · 79 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. | Hermes 4.3 36B | F16 | 87.6 GB | 56.6 tok/s | Runs great |
| 74Great quality (A) · 74 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. | Kimi Linear 48B-A3B | F16 | 112 GB | 171 tok/s | Runs great |
| 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. | Nemotron 3 Ultra 550B-A55B | Q2_K | 238 GB | 144 tok/s | Runs welltight fit |
| 80Great quality (A) · 80 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. | Nemotron Cascade 2 30B-A3B | F16 | 76.4 GB | 164 tok/s | Runs great |
| 70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Command R+ (08-2024) 104B | Q8_0 | 125 GB | 42.7 tok/s | Runs great |
| 80Great quality (A) · 80 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. | North Mini Code 1.0 (30B-A3B) | F16 | 74.5 GB | 171 tok/s | Runs great |
| 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. | MiniMax-Text-01 | Q3_K_M | 237 GB | 137 tok/s | Runs welltight fit |
| 76Great quality (A) · 76 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. | InternVL3.5 38B | F16 | 92.1 GB | 53.3 tok/s | Runs great |
| 61Good quality (B) · 61 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V2 Chat | Q6_K | 207 GB | 141 tok/s | Runs great |
| 78Great quality (A) · 78 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. | Qwen3-VL 32B Instruct | F16 | 82.1 GB | 61.3 tok/s | Runs great |
| 78Great quality (A) · 78 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. | QwQ 32B | F16 | 80.9 GB | 62.4 tok/s | Runs great |
| 74Great quality (A) · 74 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | InternVL3 78B | Q8_0 | 99.0 GB | 56.6 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 82/100 (quality, fit, speed and memory use) sets the ranking. | Llama 4 Maverick (17B x 128E) | Q3_K_M | 212 GB | 211 tok/s | Runs great |
| 78Great quality (A) · 78 of 100: how capable the model is at F16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 30B-A3B Thinking 2507 | F16 | 75.1 GB | 167 tok/s | Runs great |
| 78Great quality (A) · 78 of 100: how capable the model is at F16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Coder 30B-A3B | F16 | 75.1 GB | 167 tok/s | Runs great |
| 67Good quality (B) · 67 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. | Hermes 4 405B | Q3_K_M | 216 GB | 27.8 tok/s | Runs welltight fit |
| 61Good quality (B) · 61 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. | LongCat Flash Chat (560B) | Q2_K | 238 GB | 200 tok/s | Runs welltight fit |
| 77Great quality (A) · 77 of 100: how capable the model is at F16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3 Nano 30B-A3B | F16 | 76.4 GB | 164 tok/s | Runs great |
| 76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 32B | F16 | 80.9 GB | 62.3 tok/s | Runs great |
| 74Great quality (A) · 74 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. | Llama 3.3 70B Instruct | Q8_0 | 90.7 GB | 62.8 tok/s | Runs great |
| 76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | OpenReasoning Nemotron 32B | F16 | 80.9 GB | 62.4 tok/s | Runs great |
| 76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Skywork OR1 32B | F16 | 80.9 GB | 62.4 tok/s | Runs great |
| 74Great quality (A) · 74 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. | Hermes 4 70B | Q8_0 | 90.7 GB | 62.9 tok/s | Runs great |
| 77Great quality (A) · 77 of 100: how capable the model is at F16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 30B-A3B Instruct 2507 | F16 | 75.1 GB | 167 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 81/100 (quality, fit, speed and memory use) sets the ranking. | Jamba 1.5 Large | Q3_K_M | 209 GB | 86.3 tok/s | Runs great |
| 73Great quality (A) · 73 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. | Qwen2.5-VL 72B Instruct | Q8_0 | 93.7 GB | 60.4 tok/s | Runs great |
| 76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Olmo 3.1 32B Think | F16 | 78.4 GB | 63.4 tok/s | Runs great |
| 73Great quality (A) · 73 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. | Qwen2.5 72B Instruct | Q8_0 | 92.9 GB | 61.0 tok/s | Runs great |
| 76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-VL 30B-A3B Thinking | F16 | 76.1 GB | 167 tok/s | Runs great |
| 78Great quality (A) · 78 of 100: how capable the model is at F16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | DiffusionGemma 26B-A4B IT | F16 | 65.2 GB | 158 tok/s | Runs great |
| 76Great quality (A) · 76 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. | Granite 4.2 30B | F16 | 73.9 GB | 69.8 tok/s | Runs great |
| 83Great quality (A) · 83 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. | Gemma 4 12B | F16 | 37.8 GB | 171 tok/s | Runs great |
| 72Great quality (A) · 72 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. | DeepSeek R1 Distill Llama 70B | Q8_0 | 90.7 GB | 62.9 tok/s | Runs great |
| 72Great quality (A) · 72 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. | Tülu 3 70B | Q8_0 | 90.7 GB | 62.9 tok/s | Runs great |
| 74Great quality (A) · 74 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. | EXAONE Deep 32B | F16 | 79.3 GB | 63.9 tok/s | Runs great |
| 74Great quality (A) · 74 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. | GLM-4 32B 0414 | F16 | 78.9 GB | 62.8 tok/s | Runs great |
| 74Great quality (A) · 74 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. | GLM-Z1 32B (0414) | F16 | 78.9 GB | 62.8 tok/s | Runs great |
| 64Good quality (B) · 64 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. | Command R+ 104B (04-2024) | Q8_0 | 125 GB | 42.7 tok/s | Runs great |
| 74Great quality (A) · 74 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. | Qwen3-VL 30B-A3B Instruct | F16 | 76.1 GB | 167 tok/s | Runs great |
| 63Good quality (B) · 63 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. | Tülu 3 405B | Q3_K_M | 216 GB | 27.8 tok/s | Runs welltight fit |
| 74Great quality (A) · 74 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. | Qwen3 30B-A3B | F16 | 75.0 GB | 167 tok/s | Runs great |
| 70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | InternVL3 38B | F16 | 92.1 GB | 53.3 tok/s | Runs great |
| 76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Devstral Small 2 (24B) | F16 | 62.6 GB | 85.2 tok/s | Runs great |
| 66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.2 90B Vision Instruct | Q8_0 | 110 GB | 50.1 tok/s | Runs great |
| 72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek R1 Distill Qwen 32B | F16 | 80.9 GB | 62.3 tok/s | Runs great |
| 70Great quality (A) · 70 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.1 70B Instruct | Q8_0 | 90.7 GB | 62.8 tok/s | Runs great |
| 55Good quality (B) · 55 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Mixtral 8x22B Instruct | Q8_0 | 164 GB | 79.4 tok/s | Runs great |
| 72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Olmo 3.1 32B Instruct | F16 | 78.4 GB | 63.4 tok/s | Runs great |
| 72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | EXAONE 4.0 32B | F16 | 77.9 GB | 63.9 tok/s | Runs great |
| 72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3.5 Lightning 30B-A3B | F16 | 76.4 GB | 171 tok/s | Runs great |
| 70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-Omni 30B-A3B Instruct | F16 | 84.5 GB | 167 tok/s | Runs great |
| 68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | QVQ 72B Preview | Q8_0 | 93.7 GB | 60.4 tok/s | Runs great |
| 72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.1 30B | F16 | 73.1 GB | 70.8 tok/s | Runs great |
| 80Great quality (A) · 80 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. | K2 Horizon 7B | F16 | 32.4 GB | 227 tok/s | Runs great |
| 74Great quality (A) · 74 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. | LFM2.5 24B-A2B | F16 | 61.3 GB | 179 tok/s | Runs great |
| 70Great quality (A) · 70 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. | Qwen2.5 32B Instruct | F16 | 80.9 GB | 62.3 tok/s | Runs great |
| 70Great quality (A) · 70 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. | Baichuan M2 32B | F16 | 80.9 GB | 62.4 tok/s | Runs great |
| 70Great quality (A) · 70 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. | OpenHands LM 32B | F16 | 80.9 GB | 62.4 tok/s | Runs great |
| 68Good quality (B) · 68 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Hermes 3 (Llama 3.1 70B) | Q8_0 | 90.7 GB | 62.9 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 78/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.1 405B Instruct | Q3_K_M | 216 GB | 27.8 tok/s | Runs welltight fit |
| 72Great quality (A) · 72 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. | Gemma 3 27B IT | F16 | 68.8 GB | 74.6 tok/s | Runs great |
| 70Great quality (A) · 70 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. | Sarvam 30B | F16 | 77.7 GB | 180 tok/s | Runs great |
| 66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Apertus v1.5 70B | Q8_0 | 92.2 GB | 61.6 tok/s | Runs great |
| 68Good quality (B) · 68 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. | Qwen2.5-VL 32B Instruct | F16 | 82.2 GB | 61.1 tok/s | Runs great |
| 72Great quality (A) · 72 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. | Magistral Small 1.2 (24B) | F16 | 62.6 GB | 85.2 tok/s | Runs great |
| 78Great quality (A) · 78 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. | SenseNova Loop 9B Preview | F16 | 33.0 GB | 212 tok/s | Runs great |
| 78Great quality (A) · 78 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. | MiMo V2.6 Distill Qwen 9B | F16 | 32.3 GB | 217 tok/s | Runs great |
| 66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.1 Nemotron 70B Instruct | Q8_0 | 90.7 GB | 62.9 tok/s | Runs great |
| 70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | MedGemma 27B Text IT | F16 | 68.0 GB | 75.7 tok/s | Runs great |
| 77Great quality (A) · 77 of 100: how capable the model is at F16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.5 9B | F16 | 32.8 GB | 212 tok/s | Runs great |
| 67Good quality (B) · 67 of 100: how capable the model is at F16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 Coder 32B Instruct | F16 | 80.9 GB | 62.3 tok/s | Runs great |
| 64Good quality (B) · 64 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. | Qwen2-VL 72B Instruct | Q8_0 | 93.7 GB | 60.4 tok/s | Runs great |
| 64Good quality (B) · 64 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. | Qwen2 72B Instruct | Q8_0 | 93.0 GB | 61.0 tok/s | Runs great |
| 76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 9B | F16 | 32.8 GB | 212 tok/s | Runs great |
| 70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | Devstral Small 1.1 (24B) | F16 | 61.7 GB | 86.8 tok/s | Runs great |
| 70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | Magistral Small 2507 | F16 | 61.7 GB | 86.8 tok/s | Runs great |
| 66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | QwQ 32B Preview | F16 | 80.9 GB | 62.4 tok/s | Runs great |
| 68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Terminal RSI 27B | F16 | 69.3 GB | 73.6 tok/s | Runs great |
| 75Great quality (A) · 75 of 100: how capable the model is at F16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.0 9B | F16 | 32.8 GB | 212 tok/s | Runs great |
| 70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE 4.5 21B-A3B Thinking | F16 | 57.3 GB | 171 tok/s | Runs great |
| 70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | gpt-oss 20B | F16 | 55.2 GB | 163 tok/s | Runs great |
| 72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Apriel 1.5 15B Thinker | F16 | 44.5 GB | 138 tok/s | Runs great |
| 72Great quality (A) · 72 of 100: how capable the model is at F16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Phi-4 Reasoning Plus (14B) | F16 | 44.2 GB | 139 tok/s | Runs great |
| 70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Maple Preview (20B-A1B) | F16 | 53.7 GB | 196 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 76/100 (quality, fit, speed and memory use) sets the ranking. | Grok-1 (314B) | Q4_K_M | 207 GB | 75.6 tok/s | Runs great |
| 67Good quality (B) · 67 of 100: how capable the model is at F16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Hemmingway 1.5 | F16 | 67.5 GB | 76.0 tok/s | Runs great |
| 68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Small 3.2 24B | F16 | 62.6 GB | 85.2 tok/s | Runs great |
| 64Good quality (B) · 64 of 100: how capable the model is at F16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Falcon-H1 34B Instruct | F16 | 81.7 GB | 60.8 tok/s | Runs great |
| 68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Magistral Small 2506 | F16 | 61.7 GB | 86.8 tok/s | Runs great |
| 74Great quality (A) · 74 of 100: how capable the model is at F16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | TMax 9B | F16 | 31.4 GB | 228 tok/s | Runs great |
| 66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | SenseNova 6.8 Code2Video | F16 | 68.5 GB | 74.7 tok/s | Runs great |
| 66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | Trinity Mini (26B-A3B) | F16 | 65.6 GB | 171 tok/s | Runs great |
| 70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | Phi-4 Reasoning Vision 15B | F16 | 45.1 GB | 135 tok/s | Runs great |
| 52Fair quality (C) · 52 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. | Qwen1.5 110B Chat | Q8_0 | 134 GB | 39.9 tok/s | Runs great |
| 62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | Axion 1.0 35B | F16 | 83.6 GB | 171 tok/s | Runs great |
| 70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | Phi-4 Reasoning (14B) | F16 | 44.2 GB | 139 tok/s | Runs great |
| 66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Small 3.1 24B | F16 | 62.5 GB | 85.2 tok/s | Runs great |
| 66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | Devstral Small 2505 | F16 | 61.7 GB | 86.8 tok/s | Runs great |
| 60Good quality (B) · 60 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. | Apertus 70B Instruct | Q8_0 | 90.7 GB | 62.8 tok/s | Runs great |
| 62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | Command R (08-2024) 32B | F16 | 79.1 GB | 63.3 tok/s | Runs great |
| 62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.0 H Small (32B-A9B) | F16 | 77.8 GB | 114 tok/s | Runs great |
| 70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Mellum2.1 Thinking (12B-A2.5B) | F16 | 37.6 GB | 179 tok/s | Runs great |
| 66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Reka Flash 3.1 (21B) | F16 | 56.1 GB | 97.8 tok/s | Runs great |
| 68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 14B | F16 | 44.1 GB | 138 tok/s | Runs great |
| 58Good quality (B) · 58 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-Math 72B Instruct | Q8_0 | 91.6 GB | 61.0 tok/s | Runs great |
| 70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | UI-Mate 9B | F16 | 32.3 GB | 217 tok/s | Runs great |
| 70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | UI-Venus 2 9B | F16 | 32.3 GB | 217 tok/s | Runs great |
| 64Good quality (B) · 64 of 100: how capable the model is at F16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Small 3 24B (2501) | F16 | 61.7 GB | 86.8 tok/s | Runs great |
| 58Good quality (B) · 58 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3 70B Instruct | Q8_0 | 90.7 GB | 62.9 tok/s | Runs great |
| 60Good quality (B) · 60 of 100: how capable the model is at F16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Aya Vision 32B | F16 | 80.8 GB | 61.7 tok/s | Runs great |
| 50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2 57B-A14B Instruct | F16 | 128 GB | 89.1 tok/s | Runs great |
| 62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 2 27B IT | F16 | 69.3 GB | 75.2 tok/s | Runs great |
| 60Good quality (B) · 60 of 100: how capable the model is at F16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Aya Expanse 32B | F16 | 79.1 GB | 63.3 tok/s | Runs great |
| 60Good quality (B) · 60 of 100: how capable the model is at F16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | OLMo 2 32B Instruct | F16 | 78.7 GB | 63.4 tok/s | Runs great |
| 59Good quality (B) · 59 of 100: how capable the model is at F16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | NorthCUA Mini | F16 | 83.6 GB | 171 tok/s | Runs great |
| 70Great quality (A) · 70 of 100: how capable the model is at F16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3.5 Bolt E4B | F16 | 29.3 GB | 454 tok/s | Runs great |
| 56Good quality (B) · 56 of 100: how capable the model is at F16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3.5 MoE (42B-A6.6B) | F16 | 98.0 GB | 132 tok/s | Runs great |
| 64Good quality (B) · 64 of 100: how capable the model is at F16, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE 4.5 21B-A3B | F16 | 57.6 GB | 171 tok/s | Runs great |
| 66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Apriel Nemotron 15B Thinker | F16 | 44.8 GB | 137 tok/s | Runs great |
| 66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | AceReason Nemotron 14B | F16 | 44.4 GB | 138 tok/s | Runs great |
| 66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | OpenReasoning Nemotron 14B | F16 | 44.4 GB | 138 tok/s | Runs great |
| 66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 Coder 14B Instruct | F16 | 44.4 GB | 138 tok/s | Runs great |
| 66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Hermes 4 14B | F16 | 44.1 GB | 138 tok/s | Runs great |
| 62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Voxtral Small 24B | F16 | 63.1 GB | 84.3 tok/s | Runs great |
| 62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Dolphin Mistral 24B Venice Edition | F16 | 62.6 GB | 85.2 tok/s | Runs great |
| 66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Ministral 3 14B Reasoning | F16 | 42.4 GB | 147 tok/s | Runs great |
| 68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.2 8B | F16 | 32.1 GB | 233 tok/s | Runs great |
| 62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Codestral 22B | F16 | 59.6 GB | 91.9 tok/s | Runs great |
| 68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 E4B | F16 | 29.3 GB | 454 tok/s | Runs great |
| 52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Nous Hermes 2 Mixtral 8x7B DPO | F16 | 108 GB | 93.6 tok/s | Runs great |
| 50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Jamba 1.5 Mini | F16 | 116 GB | 97.6 tok/s | Runs great |
| 64Good quality (B) · 64 of 100: how capable the model is at F16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | InternVL3 14B | F16 | 45.1 GB | 135 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 72/100 (quality, fit, speed and memory use) sets the ranking. | Snowflake Arctic Instruct | Q3_K_M | 248 GB | 211 tok/s | Runs welltight fit |
| 54Fair quality (C) · 54 of 100: how capable the model is at F16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Command R 35B (v01) | F16 | 93.9 GB | 58.5 tok/s | Runs great |
| 64Good quality (B) · 64 of 100: how capable the model is at F16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | DeepCoder 14B Preview | F16 | 44.4 GB | 138 tok/s | Runs great |
| 64Good quality (B) · 64 of 100: how capable the model is at F16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Phi-4 (14B) | F16 | 44.3 GB | 139 tok/s | Runs great |
| 68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Nanbeige4.2 3B | F16 | 23.0 GB | 490 tok/s | Runs great |
| 64Good quality (B) · 64 of 100: how capable the model is at F16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Ministral 3 14B | F16 | 42.4 GB | 147 tok/s | Runs great |
| 60Good quality (B) · 60 of 100: how capable the model is at F16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Dolphin 3.0 R1 Mistral 24B | F16 | 61.7 GB | 86.8 tok/s | Runs great |
| 68Good quality (B) · 68 of 100: how capable the model is at F16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron Labs Dory 1.0 4B | F16 | 21.6 GB | 514 tok/s | Runs great |
| 60Good quality (B) · 60 of 100: how capable the model is at F16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Solar Pro Preview 22B | F16 | 58.8 GB | 92.4 tok/s | Runs great |
| 50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Mixtral 8x7B Instruct | F16 | 108 GB | 93.6 tok/s | Runs great |
| 62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek R1 Distill Qwen 14B | F16 | 44.4 GB | 138 tok/s | Runs great |
| 62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 14B Instruct | F16 | 44.2 GB | 139 tok/s | Runs great |
| 62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | JanusCoder 14B | F16 | 44.1 GB | 138 tok/s | Runs great |
| 66Good quality (B) · 66 of 100: how capable the model is at F16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Spark-X2.6 4B | F16 | 21.7 GB | 498 tok/s | Runs great |
| 58Good quality (B) · 58 of 100: how capable the model is at F16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | LLM4Decompile 22B V2 | F16 | 59.6 GB | 91.9 tok/s | Runs great |
| 60Good quality (B) · 60 of 100: how capable the model is at F16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Kimi-VL A3B Thinking 2506 | F16 | 46.3 GB | 171 tok/s | Runs great |
| 50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Aya 23 35B | F16 | 93.9 GB | 58.5 tok/s | Runs great |
| 60Good quality (B) · 60 of 100: how capable the model is at F16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 14B Instruct 1M | F16 | 44.4 GB | 138 tok/s | Runs great |
| 62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-VL 8B Instruct | F16 | 31.9 GB | 233 tok/s | Runs great |
| 56Good quality (B) · 56 of 100: how capable the model is at F16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | LFM2 24B-A2B | F16 | 61.0 GB | 182 tok/s | Runs great |
| 62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | InternVL3.5 8B | F16 | 31.5 GB | 240 tok/s | Runs great |
| 62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek R1 0528 Qwen3 8B | F16 | 30.8 GB | 250 tok/s | Runs great |
| 67Good quality (B) · 67 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. | Step 5 Preview (600B-A27B) | Q2_K | 256 GB | 127 tok/s | Runs welloffloads to RAM |
| 60Good quality (B) · 60 of 100: how capable the model is at F16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 3 12B IT | F16 | 38.3 GB | 168 tok/s | Runs great |
| 57Good quality (B) · 57 of 100: how capable the model is at F16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Groot 19B A3B 261023 | F16 | 52.2 GB | 171 tok/s | Runs great |
| 60Good quality (B) · 60 of 100: how capable the model is at F16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4.1V 9B Thinking | F16 | 34.1 GB | 199 tok/s | Runs great |
| 50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Yi 1.5 34B Chat | F16 | 83.0 GB | 59.5 tok/s | Runs great |
| 62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 E2B | F16 | 23.5 GB | 889 tok/s | Runs great |
| 62Good quality (B) · 62 of 100: how capable the model is at F16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 4B | F16 | 22.8 GB | 439 tok/s | Runs great |
| 60Good quality (B) · 60 of 100: how capable the model is at F16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.1 8B | F16 | 32.1 GB | 233 tok/s | Runs great |
| 60Good quality (B) · 60 of 100: how capable the model is at F16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-V 4.5 8B | F16 | 31.8 GB | 235 tok/s | Runs great |
| 60Good quality (B) · 60 of 100: how capable the model is at F16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron Nano 9B v2 | F16 | 31.1 GB | 230 tok/s | Runs great |
| 60Good quality (B) · 60 of 100: how capable the model is at F16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 8B | F16 | 30.8 GB | 250 tok/s | Runs great |
| 54Fair quality (C) · 54 of 100: how capable the model is at F16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Small 22B (2409) | F16 | 59.6 GB | 91.9 tok/s | Runs great |
| 60Good quality (B) · 60 of 100: how capable the model is at F16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Ling 3.0 Tiny (8B-A1.3B) | F16 | 29.2 GB | 200 tok/s | Runs great |
| 61Good quality (B) · 61 of 100: how capable the model is at F16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | TMax 4B | F16 | 21.9 GB | 486 tok/s | Runs great |
| 60Good quality (B) · 60 of 100: how capable the model is at F16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Mage-VL-Cowork 4.7B | F16 | 23.9 GB | 431 tok/s | Runs great |
| 60Good quality (B) · 60 of 100: how capable the model is at F16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Agents-A1 4B | F16 | 22.5 GB | 450 tok/s | Runs great |
| 58Good quality (B) · 58 of 100: how capable the model is at F16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | GLM-Z1 9B (0414) | F16 | 32.3 GB | 218 tok/s | Runs great |
| 58Good quality (B) · 58 of 100: how capable the model is at F16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | MiMo-VL 7B RL | F16 | 31.0 GB | 246 tok/s | Runs great |
| 58Good quality (B) · 58 of 100: how capable the model is at F16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Seed-Coder 8B Reasoning | F16 | 30.8 GB | 248 tok/s | Runs great |
| 60Good quality (B) · 60 of 100: how capable the model is at F16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM5 2B | F16 | 18.6 GB | 811 tok/s | Runs great |
| 58Good quality (B) · 58 of 100: how capable the model is at F16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Fara 1.5 4B | F16 | 22.5 GB | 450 tok/s | Runs great |
| 56Good quality (B) · 56 of 100: how capable the model is at F16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Ministral 3 8B | F16 | 32.2 GB | 229 tok/s | Runs great |
| 56Good quality (B) · 56 of 100: how capable the model is at F16, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | Seed-Coder 8B Instruct | F16 | 30.8 GB | 248 tok/s | Runs great |
| 56Good quality (B) · 56 of 100: how capable the model is at F16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | MiMo 7B RL | F16 | 30.1 GB | 261 tok/s | Runs great |
| 56Good quality (B) · 56 of 100: how capable the model is at F16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | EXAONE Deep 7.8B | F16 | 29.9 GB | 261 tok/s | Runs great |
| 56Good quality (B) · 56 of 100: how capable the model is at F16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | InternVL3 8B | F16 | 29.5 GB | 258 tok/s | Runs great |
| 56Good quality (B) · 56 of 100: how capable the model is at F16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Falcon-H1R 7B | F16 | 28.7 GB | 269 tok/s | Runs great |
| 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. | Code Llama 70B Instruct | Q8_0 | 87.7 GB | 64.3 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 67/100 (quality, fit, speed and memory use) sets the ranking. | Falcon 180B Chat | Q5_K_M | 141 GB | 40.1 tok/s | Runs great |
| 52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Ling Mini 2.0 (16B-A1.4B) | F16 | 46.1 GB | 198 tok/s | Runs great |
| 52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek Coder V2 Lite (16B) | F16 | 44.9 GB | 180 tok/s | Runs great |
| 50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | InternLM2.5 20B Chat | F16 | 54.5 GB | 103 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | LLaVA 1.6 34B | F16 | 83.7 GB | 58.8 tok/s | Runs great |
| 55Good quality (B) · 55 of 100: how capable the model is at F16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 Coder 7B Instruct | F16 | 28.9 GB | 268 tok/s | Runs great |
| 56Good quality (B) · 56 of 100: how capable the model is at F16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Mage-VL 4.7B | F16 | 23.9 GB | 431 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek Coder 33B Instruct | F16 | 82.0 GB | 61.3 tok/s | Runs great |
| 56Good quality (B) · 56 of 100: how capable the model is at F16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 4B Thinking 2507 | F16 | 22.4 GB | 509 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Qwen1.5 32B Chat | F16 | 80.4 GB | 62.9 tok/s | Runs great |
| 54Fair quality (C) · 54 of 100: how capable the model is at F16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.1 Nemotron Nano 8B v1 | F16 | 30.3 GB | 255 tok/s | Runs great |
| 54Fair quality (C) · 54 of 100: how capable the model is at F16, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM4 8B | F16 | 29.8 GB | 250 tok/s | Runs great |
| 54Fair quality (C) · 54 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Olmo 3 7B Think | F16 | 29.3 GB | 280 tok/s | Runs great |
| 52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Mistral Nemo 12B Instruct | F16 | 38.9 GB | 168 tok/s | Runs great |
| 54Fair quality (C) · 54 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | OpenReasoning Nemotron 7B | F16 | 28.9 GB | 268 tok/s | Runs great |
| 50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Kimi-VL A3B Instruct | F16 | 46.3 GB | 171 tok/s | Runs great |
| 56Good quality (B) · 56 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | LFM3 1.7B | F16 | 16.8 GB | 1,182 tok/s | Runs great |
| 52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Falcon 3 10B Instruct | F16 | 35.2 GB | 198 tok/s | Runs great |
| 54Fair quality (C) · 54 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-VL 4B Instruct | F16 | 23.3 GB | 461 tok/s | Runs great |
| 52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4 9B 0414 | F16 | 32.3 GB | 218 tok/s | Runs great |
| 52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | NorthCUA Nano | F16 | 32.3 GB | 217 tok/s | Runs great |
| 54Fair quality (C) · 54 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 4B Instruct 2507 | F16 | 22.4 GB | 509 tok/s | Runs great |
| 52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-o 2.6 8B | F16 | 31.0 GB | 236 tok/s | Runs great |
| 52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Foundation-Sec 8B Reasoning | F16 | 30.3 GB | 255 tok/s | Runs great |
| 52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-VL 7B Instruct | F16 | 30.2 GB | 247 tok/s | Runs great |
| 52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | LFM2.5 8B-A1B | F16 | 30.2 GB | 196 tok/s | Runs great |
| 50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Pixtral 12B (2409) | F16 | 39.3 GB | 165 tok/s | Runs great |
| 52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Hunyuan 7B Instruct | F16 | 29.3 GB | 273 tok/s | Runs great |
| 52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 66/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 7B Instruct | F16 | 28.9 GB | 268 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. | DeepSeek LLM 67B Chat | Q8_0 | 86.2 GB | 65.8 tok/s | Runs great |
| 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Yi 34B Chat | F16 | 83.0 GB | 59.5 tok/s | Runs great |
| 50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 2 9B IT | F16 | 33.3 GB | 221 tok/s | Runs great |
| 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Granite Code 34B Instruct | F16 | 81.0 GB | 60.6 tok/s | Runs great |
| 50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | InternLM3 8B Instruct | F16 | 31.2 GB | 232 tok/s | Runs great |
| 52Fair quality (C) · 52 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.2 3B | F16 | 21.2 GB | 559 tok/s | Runs great |
| 50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | InternVL2.5 8B | F16 | 30.4 GB | 253 tok/s | Runs great |
| 50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek R1 Distill Llama 8B | F16 | 30.3 GB | 255 tok/s | Runs great |
| 50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Foundation-Sec 1.1 8B Instruct | F16 | 30.3 GB | 255 tok/s | Runs great |
| 50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Fara 7B | F16 | 30.2 GB | 247 tok/s | Runs great |
| 50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | GLiDE 9B | F16 | 29.3 GB | 258 tok/s | Runs great |
| 50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Olmo 3 7B Instruct | F16 | 29.3 GB | 280 tok/s | Runs great |
| 50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 7B Instruct 1M | F16 | 28.9 GB | 268 tok/s | Runs great |
| 50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Falcon-H1 7B Instruct | F16 | 28.7 GB | 269 tok/s | Runs great |
| 46Fair quality (C) · 46 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Moonlight 16B-A3B Instruct | F16 | 45.4 GB | 171 tok/s | Runs great |
| 50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Qianfan-OCR 4B | F16 | 23.9 GB | 431 tok/s | Runs great |
| 38Basic quality (D) · 38 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Code Llama 34B Instruct | F16 | 82.3 GB | 60.6 tok/s | Runs great |
| 46Fair quality (C) · 46 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3 Medium 128K Instruct | F16 | 42.8 GB | 146 tok/s | Runs great |
| 48Fair quality (C) · 48 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4 9B Chat 1M | F16 | 32.8 GB | 216 tok/s | Runs great |
| 48Fair quality (C) · 48 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4 9B Chat (2024) | F16 | 32.3 GB | 218 tok/s | Runs great |
| 50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 4B | F16 | 22.4 GB | 509 tok/s | Runs great |
| 46Fair quality (C) · 46 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3 Medium (14B) | F16 | 42.0 GB | 146 tok/s | Runs great |
| 50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3 Nano 4B | F16 | 21.3 GB | 515 tok/s | Runs great |
| 48Fair quality (C) · 48 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Hermes 3 (Llama 3.1 8B) | F16 | 30.3 GB | 255 tok/s | Runs great |
| 48Fair quality (C) · 48 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.1 8B Instruct | F16 | 30.3 GB | 255 tok/s | Runs great |
| 48Fair quality (C) · 48 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-V 2.6 8B | F16 | 29.9 GB | 252 tok/s | Runs great |
| 36Basic quality (D) · 36 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. | Llama 2 70B Chat | Q8_0 | 87.7 GB | 64.3 tok/s | Runs great |
| 50Fair quality (C) · 50 of 100: how capable the model is at F16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | LFM3-VL 2B | F16 | 17.1 GB | 1,065 tok/s | Runs great |
| 46Fair quality (C) · 46 of 100: how capable the model is at F16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-Omni 7B | F16 | 35.1 GB | 191 tok/s | Runs great |
| 42Fair quality (C) · 42 of 100: how capable the model is at F16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | InternLM2 Chat 20B | F16 | 54.5 GB | 103 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | OLMo 2 13B Instruct | F16 | 44.0 GB | 149 tok/s | Runs great |
| 48Fair quality (C) · 48 of 100: how capable the model is at F16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Chandra OCR 2 | F16 | 24.1 GB | 386 tok/s | Runs great |
| 48Fair quality (C) · 48 of 100: how capable the model is at F16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | LightOnOCR-3 4B | F16 | 22.5 GB | 450 tok/s | Runs great |
| 46Fair quality (C) · 46 of 100: how capable the model is at F16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | CodeGeeX4 All 9B | F16 | 32.3 GB | 218 tok/s | Runs great |
| 46Fair quality (C) · 46 of 100: how capable the model is at F16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Apertus v1.5 8B | F16 | 32.1 GB | 230 tok/s | Runs great |
| 46Fair quality (C) · 46 of 100: how capable the model is at F16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.2 8B Instruct | F16 | 30.9 GB | 250 tok/s | Runs great |
| 46Fair quality (C) · 46 of 100: how capable the model is at F16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.3 8B | F16 | 30.9 GB | 250 tok/s | Runs great |
| 46Fair quality (C) · 46 of 100: how capable the model is at F16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Ministral 8B (2410) | F16 | 30.4 GB | 255 tok/s | Runs great |
| 46Fair quality (C) · 46 of 100: how capable the model is at F16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | DeepHermes 3 Llama 3 8B Preview | F16 | 30.3 GB | 255 tok/s | Runs great |
| 46Fair quality (C) · 46 of 100: how capable the model is at F16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Dolphin 3.0 Llama 3.1 8B | F16 | 30.3 GB | 255 tok/s | Runs great |
| 46Fair quality (C) · 46 of 100: how capable the model is at F16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Tülu 3 8B | F16 | 30.3 GB | 255 tok/s | Runs great |
| 46Fair quality (C) · 46 of 100: how capable the model is at F16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | EXAONE 3.5 7.8B | F16 | 29.9 GB | 261 tok/s | Runs great |
| 46Fair quality (C) · 46 of 100: how capable the model is at F16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Falcon 3 7B Instruct | F16 | 29.1 GB | 274 tok/s | Runs great |
| 46Fair quality (C) · 46 of 100: how capable the model is at F16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 3n E4B | F16 | 29.0 GB | 511 tok/s | Runs great |
| 46Fair quality (C) · 46 of 100: how capable the model is at F16, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek R1 Distill Qwen 7B | F16 | 28.9 GB | 268 tok/s | Runs great |
| 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | InternLM2 Math Plus 20B | F16 | 54.5 GB | 103 tok/s | Runs great |
| 46Fair quality (C) · 46 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Phi-4 Mini Reasoning (3.8B) | F16 | 22.0 GB | 533 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.1 8B Instruct | F16 | 30.9 GB | 250 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Aya Vision 8B | F16 | 30.8 GB | 237 tok/s | Runs great |
| 46Fair quality (C) · 46 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.1 3B | F16 | 20.7 GB | 601 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | InternVL2 8B | F16 | 30.4 GB | 253 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Dolphin 2.9.4 Llama 3.1 8B | F16 | 30.3 GB | 255 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Hermes 2 Pro Llama 3 8B | F16 | 30.3 GB | 255 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | OpenChat 3.6 8B | F16 | 30.3 GB | 255 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2-VL 7B Instruct | F16 | 30.2 GB | 247 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Command R7B | F16 | 29.6 GB | 255 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3 Small 8K Instruct | F16 | 29.1 GB | 277 tok/s | Runs great |
| 45Fair quality (C) · 45 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | WeVisOne-VL 4B | F16 | 24.1 GB | 423 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2 7B Instruct | F16 | 28.9 GB | 268 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.0 H Tiny (7B-A1B) | F16 | 27.1 GB | 206 tok/s | Runs great |
| 38Basic quality (D) · 38 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | CogVLM2 Llama 3 Chat 19B | F16 | 56.5 GB | 105 tok/s | Runs great |
| 45Fair quality (C) · 45 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 3 4B IT | F16 | 22.0 GB | 476 tok/s | Runs great |
| 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | StarCoder2 15B Instruct | F16 | 45.8 GB | 128 tok/s | Runs great |
| 42Fair quality (C) · 42 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.2 11B Vision Instruct | F16 | 35.9 GB | 192 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Phi-4 Multimodal Instruct | F16 | 25.4 GB | 367 tok/s | Runs great |
| 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek V2 Lite Chat | F16 | 44.9 GB | 180 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.1 Nemotron Nano 4B v1.1 | F16 | 23.3 GB | 453 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | MedGemma 4B IT | F16 | 22.0 GB | 476 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Phi-4 Mini (3.8B) | F16 | 22.0 GB | 533 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Ministral 3 3B | F16 | 21.8 GB | 531 tok/s | Runs great |
| 42Fair quality (C) · 42 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Mistral-NeMo-Minitron 8B Instruct | F16 | 31.4 GB | 243 tok/s | Runs great |
| 42Fair quality (C) · 42 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3 8B Instruct | F16 | 30.3 GB | 255 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Unlimited OCR 2 (3B-A0.6B) | F16 | 20.4 GB | 214 tok/s | Runs great |
| 42Fair quality (C) · 42 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Command R7B Arabic | F16 | 29.6 GB | 255 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Jamba Reasoning 3B | F16 | 19.6 GB | 639 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | LFM2.5-VL 3B | F16 | 19.6 GB | 655 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | North Micro Vision | F16 | 19.1 GB | 825 tok/s | Runs great |
| 44Fair quality (C) · 44 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | LFM2.5 2.6B | F16 | 18.7 GB | 757 tok/s | Runs great |
| 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Nous Hermes 2 SOLAR 10.7B | F16 | 35.5 GB | 191 tok/s | Runs great |
| 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | SOLAR 10.7B Instruct | F16 | 35.5 GB | 191 tok/s | Runs great |
| 36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | Granite Code 20B Instruct | F16 | 53.6 GB | 102 tok/s | Runs great |
| 42Fair quality (C) · 42 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | Hunyuan 4B Instruct | F16 | 22.8 GB | 485 tok/s | Runs great |
| 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | Yi Coder 9B Chat | F16 | 31.7 GB | 232 tok/s | Runs great |
| 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek Prover V2 7B | F16 | 31.0 GB | 296 tok/s | Runs great |
| 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | Apertus 8B Instruct | F16 | 30.4 GB | 254 tok/s | Runs great |
| 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | Aya Expanse 8B | F16 | 30.3 GB | 255 tok/s | Runs great |
| 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.0 8B Instruct | F16 | 30.2 GB | 250 tok/s | Runs great |
| 42Fair quality (C) · 42 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | SmolLM3 3B | F16 | 20.0 GB | 664 tok/s | Runs great |
| 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | InternLM2.5 7B Chat | F16 | 29.8 GB | 264 tok/s | Runs great |
| 42Fair quality (C) · 42 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | Jamba2 3B | F16 | 19.3 GB | 675 tok/s | Runs great |
| 42Fair quality (C) · 42 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-OCR 1.0 1.3B | F16 | 15.9 GB | 1,573 tok/s | Runs great |
| 42Fair quality (C) · 42 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | PaddleOCR-VL 1.6 0.9B | F16 | 15.3 GB | 2,130 tok/s | Runs great |
| 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3.5 Mini Instruct | F16 | 24.1 GB | 535 tok/s | Runs great |
| 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | AFM 4.5B | F16 | 23.0 GB | 443 tok/s | Runs great |
| 38Basic quality (D) · 38 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | LLM4Decompile 9B V2 | F16 | 31.7 GB | 232 tok/s | Runs great |
| 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.0 Micro (3B) | F16 | 20.7 GB | 601 tok/s | Runs great |
| 38Basic quality (D) · 38 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Dolphin 2.9 Llama 3 8B | F16 | 30.3 GB | 255 tok/s | Runs great |
| 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Unlimited OCR (3B-A0.6B) | F16 | 20.4 GB | 214 tok/s | Runs great |
| 38Basic quality (D) · 38 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | LFM2 8B-A1B | F16 | 30.0 GB | 196 tok/s | Runs great |
| 38Basic quality (D) · 38 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | EXAONE 3.0 7.8B Instruct | F16 | 29.4 GB | 261 tok/s | Runs great |
| 38Basic quality (D) · 38 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Mistral 7B Instruct v0.3 | F16 | 28.8 GB | 282 tok/s | Runs great |
| 38Basic quality (D) · 38 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Zamba2 7B Instruct | F16 | 28.7 GB | 278 tok/s | Runs great |
| 34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Qwen1.5 14B Chat | F16 | 48.3 GB | 144 tok/s | Runs great |
| 38Basic quality (D) · 38 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Falcon3 Mamba 7B Instruct | F16 | 27.8 GB | 281 tok/s | Runs great |
| 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 2B | F16 | 17.8 GB | 901 tok/s | Runs great |
| 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | TMax 2B | F16 | 17.1 GB | 1,088 tok/s | Runs great |
| 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | TeleOCR | F16 | 17.0 GB | 1,440 tok/s | Runs great |
| 40Fair quality (C) · 40 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-V 4.7 1B | F16 | 16.4 GB | 1,319 tok/s | Runs great |
| 38Basic quality (D) · 38 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3.5 Vision Instruct | F16 | 24.7 GB | 493 tok/s | Runs great |
| 38Basic quality (D) · 38 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM3 4B | F16 | 21.6 GB | 502 tok/s | Runs great |
| 36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Yi 1.5 9B Chat | F16 | 31.3 GB | 232 tok/s | Runs great |
| 36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | OLMo 2 7B Instruct | F16 | 29.9 GB | 280 tok/s | Runs great |
| 38Basic quality (D) · 38 of 100: how capable the model is at F16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.0 H Micro | F16 | 19.6 GB | 641 tok/s | Runs great |
| 36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Hermes 2 Pro Mistral 7B | F16 | 28.8 GB | 282 tok/s | Runs great |
| 36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Starling LM 7B Beta | F16 | 28.8 GB | 282 tok/s | Runs great |
| 36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-Math 7B Instruct | F16 | 28.7 GB | 268 tok/s | Runs great |
| 36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Codestral Mamba 7B | F16 | 27.8 GB | 280 tok/s | Runs great |
| 37Basic quality (D) · 37 of 100: how capable the model is at F16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | S5 nano | F16 | 22.8 GB | 439 tok/s | Runs great |
| 32Basic quality (D) · 32 of 100: how capable the model is at F16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | StarCoder2 15B (base) | F16 | 45.8 GB | 128 tok/s | Runs great |
| 34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | CodeGemma 7B | F16 | 34.0 GB | 239 tok/s | Runs great |
| 36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 3n E2B | F16 | 24.2 GB | 1,022 tok/s | Runs great |
| 36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3 Mini 128K Instruct | F16 | 24.1 GB | 535 tok/s | Runs great |
| 35Basic quality (D) · 35 of 100: how capable the model is at F16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | OpenChat 3.5 (0106) | F16 | 28.8 GB | 282 tok/s | Runs great |
| 36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Voxtral Mini 3B | F16 | 23.6 GB | 437 tok/s | Runs great |
| 34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | RecurrentGemma 9B IT | F16 | 32.6 GB | 212 tok/s | Runs great |
| 36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3 Mini 4K Instruct | F16 | 22.5 GB | 535 tok/s | Runs great |
| 34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek Coder 6.7B Instruct | F16 | 31.0 GB | 303 tok/s | Runs great |
| 34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Aya 23 8B | F16 | 30.3 GB | 255 tok/s | Runs great |
| 36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Falcon-H1 3B Instruct | F16 | 19.8 GB | 649 tok/s | Runs great |
| 36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 Coder 3B Instruct | F16 | 19.7 GB | 662 tok/s | Runs great |
| 34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Mathstral 7B | F16 | 28.8 GB | 282 tok/s | Runs great |
| 34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Mistral 7B Instruct v0.2 | F16 | 28.8 GB | 282 tok/s | Runs great |
| 34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Nous Hermes 2 Mistral 7B DPO | F16 | 28.8 GB | 282 tok/s | Runs great |
| 34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | OpenChat 3.5 (1210) | F16 | 28.8 GB | 282 tok/s | Runs great |
| 36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-VL 2B Instruct | F16 | 18.4 GB | 960 tok/s | Runs great |
| 30Basic quality (D) · 30 of 100: how capable the model is at F16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Code Llama 13B Instruct | F16 | 46.0 GB | 157 tok/s | Runs great |
| 35Basic quality (D) · 35 of 100: how capable the model is at F16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Llama 3.2 3B Instruct | F16 | 20.6 GB | 637 tok/s | Runs great |
| 35Basic quality (D) · 35 of 100: how capable the model is at F16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Raon 1 nano | F16 | 20.5 GB | 579 tok/s | Runs great |
| 36Basic quality (D) · 36 of 100: how capable the model is at F16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM5 1B | F16 | 15.6 GB | 1,893 tok/s | Runs great |
| 34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Phi-3 Vision 128K Instruct | F16 | 24.7 GB | 493 tok/s | Runs great |
| 32Basic quality (D) · 32 of 100: how capable the model is at F16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | LLM4Decompile 6.7B V2 | F16 | 31.0 GB | 303 tok/s | Runs great |
| 34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-VL 3B Instruct | F16 | 21.0 GB | 545 tok/s | Runs great |
| 32Basic quality (D) · 32 of 100: how capable the model is at F16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Granite Code 8B Instruct (128K) | F16 | 30.5 GB | 254 tok/s | Runs great |
| 32Basic quality (D) · 32 of 100: how capable the model is at F16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | InternLM2 Math Plus 7B | F16 | 29.8 GB | 264 tok/s | Runs great |
| 34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 3B Instruct | F16 | 19.7 GB | 662 tok/s | Runs great |
| 32Basic quality (D) · 32 of 100: how capable the model is at F16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | OpenHermes 2.5 Mistral 7B | F16 | 28.8 GB | 282 tok/s | Runs great |
| 32Basic quality (D) · 32 of 100: how capable the model is at F16, whatever it runs on. Match score 57/100 (quality, fit, speed and memory use) sets the ranking. | Starling LM 7B Alpha | F16 | 28.8 GB | 282 tok/s | Runs great |
| 34Basic quality (D) · 34 of 100: how capable the model is at F16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | LFM2 2.6B | F16 | 18.5 GB | 796 tok/s | Runs great |
| 28Basic quality (D) · 28 of 100: how capable the model is at F16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Orca 2 13B | F16 | 42.6 GB | 157 tok/s | Runs great |
| 30Basic quality (D) · 30 of 100: how capable the model is at F16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | SQLCoder 7B v2 | F16 | 31.0 GB | 303 tok/s | Runs great |
| 32Basic quality (D) · 32 of 100: how capable the model is at F16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Hermes 3 Llama 3.2 3B | F16 | 20.6 GB | 637 tok/s | Runs great |
| 30Basic quality (D) · 30 of 100: how capable the model is at F16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Mistral 7B Instruct v0.1 | F16 | 28.8 GB | 282 tok/s | Runs great |
| 28Basic quality (D) · 28 of 100: how capable the model is at F16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | StableLM 2 12B Chat | F16 | 38.3 GB | 168 tok/s | Runs great |
| 16Basic quality (D) · 16 of 100: how capable the model is at F16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Falcon 40B Instruct | F16 | 97.1 GB | 48.9 tok/s | Runs great |
| 30Basic quality (D) · 30 of 100: how capable the model is at F16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Falcon Mamba 7B Instruct | F16 | 27.8 GB | 281 tok/s | Runs great |
| 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | DeepSeek MoE 16B Chat | F16 | 46.9 GB | 174 tok/s | Runs great |
| 32Basic quality (D) · 32 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | LFM2.5 1.2B Instruct | F16 | 15.6 GB | 1,748 tok/s | Runs great |
| 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | StarCoder 15B | F16 | 45.0 GB | 129 tok/s | Runs great |
| 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Baichuan 2 13B Chat | F16 | 44.4 GB | 147 tok/s | Runs great |
| 30Basic quality (D) · 30 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5-Omni 3B | F16 | 24.6 GB | 369 tok/s | Runs great |
| 28Basic quality (D) · 28 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 1.1 7B IT | F16 | 34.0 GB | 239 tok/s | Runs great |
| 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Llama 2 13B Chat | F16 | 42.6 GB | 157 tok/s | Runs great |
| 30Basic quality (D) · 30 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Falcon 3 3B Instruct | F16 | 20.4 GB | 633 tok/s | Runs great |
| 28Basic quality (D) · 28 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | LLaVA 1.6 Mistral 7B | F16 | 29.4 GB | 270 tok/s | Runs great |
| 30Basic quality (D) · 30 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.2 2B Instruct | F16 | 18.9 GB | 808 tok/s | Runs great |
| 30Basic quality (D) · 30 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.3 2B | F16 | 18.9 GB | 808 tok/s | Runs great |
| 28Basic quality (D) · 28 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Neural Chat 7B v3.3 | F16 | 28.8 GB | 282 tok/s | Runs great |
| 30Basic quality (D) · 30 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | EXAONE 3.5 2.4B | F16 | 18.6 GB | 848 tok/s | Runs great |
| 30Basic quality (D) · 30 of 100: how capable the model is at F16, whatever it runs on. Match score 55/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 1.7B | F16 | 18.2 GB | 1,007 tok/s | Runs great |
| 30Basic quality (D) · 30 of 100: how capable the model is at F16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | EXAONE 4.0 1.2B | F16 | 16.3 GB | 1,598 tok/s | Runs great |
| 28Basic quality (D) · 28 of 100: how capable the model is at F16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Yi 1.5 6B Chat | F16 | 25.6 GB | 337 tok/s | Runs great |
| 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 7B IT | F16 | 34.0 GB | 239 tok/s | Runs great |
| 24Basic quality (D) · 24 of 100: how capable the model is at F16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Qwen1.5 MoE A2.7B Chat | F16 | 43.5 GB | 176 tok/s | Runs great |
| 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Qwen1.5 7B Chat | F16 | 32.9 GB | 265 tok/s | Runs great |
| 28Basic quality (D) · 28 of 100: how capable the model is at F16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.1 2B Instruct | F16 | 18.9 GB | 808 tok/s | Runs great |
| 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | WizardMath 7B v1.1 | F16 | 28.8 GB | 282 tok/s | Runs great |
| 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Zephyr 7B Beta | F16 | 28.8 GB | 282 tok/s | Runs great |
| 28Basic quality (D) · 28 of 100: how capable the model is at F16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 2 2B | F16 | 18.9 GB | 783 tok/s | Runs great |
| 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | OLMoE 1B-7B Instruct | F16 | 27.6 GB | 200 tok/s | Runs great |
| 28Basic quality (D) · 28 of 100: how capable the model is at F16, whatever it runs on. Match score 54/100 (quality, fit, speed and memory use) sets the ranking. | Granite 4.0 H 1B | F16 | 16.2 GB | 1,401 tok/s | Runs great |
| 27Basic quality (D) · 27 of 100: how capable the model is at F16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | WeVisOne VL 2B | F16 | 19.0 GB | 838 tok/s | Runs great |
| 22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | LLaVA 1.5 13B | F16 | 43.3 GB | 153 tok/s | Runs great |
| 22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | WizardLM 13B v1.2 | F16 | 42.6 GB | 157 tok/s | Runs great |
| 24Basic quality (D) · 24 of 100: how capable the model is at F16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | Code Llama 7B Instruct | F16 | 31.0 GB | 303 tok/s | Runs great |
| 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | Granite Vision 3.2 2B | F16 | 19.8 GB | 686 tok/s | Runs great |
| 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | Granite 3.0 2B Instruct | F16 | 18.8 GB | 777 tok/s | Runs great |
| 24Basic quality (D) · 24 of 100: how capable the model is at F16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | StarCoder2 7B | F16 | 28.1 GB | 285 tok/s | Runs great |
| 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | DeepScaleR 1.5B Preview | F16 | 17.0 GB | 1,149 tok/s | Runs great |
| 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 Coder 1.5B Instruct | F16 | 16.5 GB | 1,328 tok/s | Runs great |
| 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | Falcon-H1 1.5B Instruct | F16 | 16.5 GB | 1,319 tok/s | Runs great |
| 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | LFM2 1.2B | F16 | 15.6 GB | 1,748 tok/s | Runs great |
| 26Basic quality (D) · 26 of 100: how capable the model is at F16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 0.8B | F16 | 15.0 GB | 2,350 tok/s | Runs great |
| 20Basic quality (D) · 20 of 100: how capable the model is at F16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | Vicuna 13B v1.5 | F16 | 42.6 GB | 157 tok/s | Runs great |
| 24Basic quality (D) · 24 of 100: how capable the model is at F16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | SmolVLM2 2.2B Instruct | F16 | 19.3 GB | 909 tok/s | Runs great |
| 22Basic quality (D) · 22 of 100: how capable the model is at F16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | Orca 2 7B | F16 | 28.8 GB | 303 tok/s | Runs great |
| 24Basic quality (D) · 24 of 100: how capable the model is at F16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2-VL 2B Instruct | F16 | 17.9 GB | 925 tok/s | Runs great |
| 24Basic quality (D) · 24 of 100: how capable the model is at F16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | Qwen2.5 1.5B Instruct | F16 | 16.5 GB | 1,328 tok/s | Runs great |
| 24Basic quality (D) · 24 of 100: how capable the model is at F16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | LFM2-VL 1.6B | F16 | 16.5 GB | 1,294 tok/s | Runs great |
| 22Basic quality (D) · 22 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. | Nemotron Mini 4B Instruct | F16 | 22.1 GB | 488 tok/s | Runs great |
| 20Basic quality (D) · 20 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. | Baichuan 2 7B Chat | F16 | 30.4 GB | 272 tok/s | Runs great |
| 22Basic quality (D) · 22 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. | SmolVLM 2.2B Instruct | F16 | 19.3 GB | 909 tok/s | Runs great |
| 20Basic quality (D) · 20 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. | Llama 2 7B Chat | F16 | 28.8 GB | 303 tok/s | Runs great |
| 22Basic quality (D) · 22 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. | Zamba2 2.7B Instruct | F16 | 18.9 GB | 769 tok/s | Runs great |
| 22Basic quality (D) · 22 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. | Hunyuan 1.8B Instruct | F16 | 17.3 GB | 1,142 tok/s | Runs great |
| 22Basic quality (D) · 22 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. | DeepSeek R1 Distill Qwen 1.5B | F16 | 17.0 GB | 1,149 tok/s | Runs great |
| 22Basic quality (D) · 22 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. | Llama 3.2 1B Instruct | F16 | 15.9 GB | 1,649 tok/s | Runs great |
| 20Basic quality (D) · 20 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. | Yi 6B Chat | F16 | 25.6 GB | 337 tok/s | Runs great |
| 20Basic quality (D) · 20 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. | Granite Code 3B Instruct (128K) | F16 | 22.8 GB | 588 tok/s | Runs great |
| 21Basic quality (D) · 21 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. | d1 2B | F16 | 17.1 GB | 1,065 tok/s | Runs great |
| 20Basic quality (D) · 20 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. | Stable Code Instruct 3B | F16 | 21.5 GB | 730 tok/s | Runs great |
| 20Basic quality (D) · 20 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. | Granite 3.1 3B-A800M Instruct | F16 | 20.3 GB | 210 tok/s | Runs great |
| 18Basic quality (D) · 18 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. | DeepSeek LLM 7B Chat | F16 | 29.0 GB | 296 tok/s | Runs great |
| 20Basic quality (D) · 20 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. | SmolLM2 1.7B Instruct | F16 | 18.2 GB | 1,196 tok/s | Runs great |
| 20Basic quality (D) · 20 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. | Qwen2.5-Math 1.5B Instruct | F16 | 16.4 GB | 1,328 tok/s | Runs great |
| 20Basic quality (D) · 20 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. | Gemma 3 1B | F16 | 15.3 GB | 2,045 tok/s | Runs great |
| 18Basic quality (D) · 18 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. | Granite 3.0 3B-A800M Instruct | F16 | 20.2 GB | 210 tok/s | Runs great |
| 16Basic quality (D) · 16 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. | LLaVA 1.5 7B | F16 | 29.5 GB | 290 tok/s | Runs great |
| 18Basic quality (D) · 18 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. | StarCoder2 3B | F16 | 19.5 GB | 675 tok/s | Runs great |
| 18Basic quality (D) · 18 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. | InternLM2.5 1.8B Chat | F16 | 17.8 GB | 1,082 tok/s | Runs great |
| 18Basic quality (D) · 18 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 700M | F16 | 14.8 GB | 2,763 tok/s | Runs great |
| 17Basic quality (D) · 17 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. | GLiDE 2B | F16 | 17.1 GB | 1,088 tok/s | Runs great |
| 16Basic quality (D) · 16 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. | StableLM Zephyr 3B | F16 | 20.1 GB | 730 tok/s | Runs great |
| 16Basic quality (D) · 16 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. | Phi-2 2.7B | F16 | 19.4 GB | 736 tok/s | Runs great |
| 14Basic quality (D) · 14 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. | Vicuna 7B v1.5 | F16 | 28.8 GB | 303 tok/s | Runs great |
| 14Basic quality (D) · 14 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. | OLMo 7B Instruct | F16 | 28.1 GB | 297 tok/s | Runs great |
| 16Basic quality (D) · 16 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. | Yi Coder 1.5B Chat | F16 | 17.8 GB | 1,382 tok/s | Runs great |
| 16Basic quality (D) · 16 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. | Falcon 3 1B Instruct | F16 | 17.1 GB | 1,224 tok/s | Runs great |
| 16Basic quality (D) · 16 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. | Spark X2.6 1.7B | F16 | 16.7 GB | 1,196 tok/s | Runs great |
| 16Basic quality (D) · 16 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 1.5B Instruct | F16 | 16.5 GB | 1,328 tok/s | Runs great |
| 15Basic quality (D) · 15 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. | surya ocr 2.5 | F16 | 14.7 GB | 2,963 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. | InternLM 7B | F16 | 28.9 GB | 279 tok/s | Runs great |
| 14Basic quality (D) · 14 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. | CodeGemma 2B | F16 | 18.4 GB | 815 tok/s | Runs great |
| 14Basic quality (D) · 14 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. | SmolLM 1.7B Instruct | F16 | 17.0 GB | 1,196 tok/s | Runs great |
| 14Basic quality (D) · 14 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. | OLMo 2 1B Instruct | F16 | 16.7 GB | 1,382 tok/s | Runs great |
| 14Basic quality (D) · 14 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. | Qwen3 0.6B | F16 | 15.6 GB | 2,726 tok/s | Runs great |
| 14Basic quality (D) · 14 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. | Falcon-H1 0.5B Instruct | F16 | 14.4 GB | 3,932 tok/s | Runs great |
| 14Basic quality (D) · 14 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 350M | F16 | 14.0 GB | 5,842 tok/s | Runs great |
| 12Basic quality (D) · 12 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. | Gemma 2B IT | F16 | 18.4 GB | 815 tok/s | Runs great |
| 12Basic quality (D) · 12 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. | DeepSeek Coder 1.3B Instruct | F16 | 17.5 GB | 1,515 tok/s | Runs great |
| 12Basic quality (D) · 12 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. | LLM4Decompile 1.3B V2 | F16 | 17.5 GB | 1,515 tok/s | Runs great |
| 12Basic quality (D) · 12 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. | LFM2-VL 450M | F16 | 14.2 GB | 4,544 tok/s | Runs great |
| 12Basic quality (D) · 12 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. | LFM2 350M | F16 | 14.0 GB | 5,842 tok/s | Runs great |
| 12Basic quality (D) · 12 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. | Granite 4.0 H 350M | F16 | 13.9 GB | 6,014 tok/s | Runs great |
| 11Basic quality (D) · 11 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. | GLiDE 0.8B | F16 | 14.8 GB | 2,726 tok/s | Runs great |
| 10Basic quality (D) · 10 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. | StableLM 2 1.6B Chat | F16 | 17.3 GB | 1,247 tok/s | Runs great |
| 10Basic quality (D) · 10 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. | StableLM 2 Zephyr 1.6B | F16 | 17.3 GB | 1,247 tok/s | Runs great |
| 10Basic quality (D) · 10 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. | SmolVLM 500M Instruct | F16 | 14.6 GB | 4,009 tok/s | Runs great |
| 10Basic quality (D) · 10 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. | Qwen2.5 0.5B Instruct | F16 | 14.3 GB | 4,173 tok/s | Runs great |
| 10Basic quality (D) · 10 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. | LFM2.5 230M | F16 | 13.7 GB | 8,890 tok/s | Runs great |
| 6Basic quality (D) · 6 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. | Falcon 7B Instruct | F16 | 27.7 GB | 283 tok/s | Runs great |
| 8Basic quality (D) · 8 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. | Hunyuan 0.5B Instruct | F16 | 15.1 GB | 3,787 tok/s | Runs great |
| 8Basic quality (D) · 8 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. | Qwen2.5 Coder 0.5B Instruct | F16 | 14.3 GB | 4,173 tok/s | Runs great |
| 8Basic quality (D) · 8 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 360M Instruct | F16 | 14.3 GB | 5,680 tok/s | Runs great |
| 6Basic quality (D) · 6 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. | TinyLlama 1.1B Chat | F16 | 15.4 GB | 1,859 tok/s | Runs great |
| 6Basic quality (D) · 6 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. | Qwen2 0.5B Instruct | F16 | 14.3 GB | 4,173 tok/s | Runs great |
| 6Basic quality (D) · 6 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. | ERNIE 4.5 0.3B | F16 | 14.1 GB | 5,680 tok/s | Runs great |
| 6Basic quality (D) · 6 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. | SmolVLM 256M Instruct | F16 | 13.9 GB | 7,865 tok/s | Runs great |
| 6Basic quality (D) · 6 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. | Gemma 3 270M | F16 | 13.8 GB | 7,573 tok/s | Runs great |
| 5Basic quality (D) · 5 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 360M Instruct | F16 | 14.0 GB | 5,680 tok/s | Runs great |
| 4Basic quality (D) · 4 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. | SmolLM2 135M Instruct | F16 | 13.6 GB | 15,729 tok/s | Runs great |
| 3Basic quality (D) · 3 of 100: how capable the model is at F16, whatever it runs on. Match score 42/100 (quality, fit, speed and memory use) sets the ranking. | Falcon-H1 Tiny 90M Instruct | F16 | 13.5 GB | 22,720 tok/s | Runs great |
| 2Basic quality (D) · 2 of 100: how capable the model is at F16, whatever it runs on. Match score 42/100 (quality, fit, speed and memory use) sets the ranking. | SmolLM 135M Instruct | F16 | 13.5 GB | 15,729 tok/s | Runs great |
| 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 | 1,125 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 | 319 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 | 315 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 | 992 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 | 1,125 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 | 725 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 | 423 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 | 319 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 | 435 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 | 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. | Hunyuan Hy4 Preview (780B) | Q2_K | 326 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 | 343 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 | 674 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 | 425 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 | 423 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 | 315 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 | 653 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 | 315 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 | 425 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 | 425 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 | 288 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 | 395 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 | 288 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 | 424 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 | 288 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 | 423 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 | 282 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 | 288 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 | 288 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 | 424 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 | 416 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 | 284 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 | 424 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 | 288 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 | 282 GB | — | Won't run |
Image models on the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax H3 Image | FP16 | 138 GB | 10 s | Runs great |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at FP16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | HunyuanImage 3.0 (80B-A13B) | FP16 | 170 GB | 61 s | Slow |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | Krea 2 Turbo | FP16 | 37.4 GB | 4.4 s | Runs great |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [dev] | FP16 | 116 GB | 37 s | Runs well |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at FP16, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image 2.1 Turbo | FP16 | 46.7 GB | 12 s | Runs great |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at FP16, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | FLUX 3 Image Klein | FP16 | 22.4 GB | 5.8 s | Runs great |
| 84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 9B | FP16 | 37.1 GB | 1.8 s | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Ming-Image 0.1 Design | FP16 | 63.9 GB | 17 s | Runs well |
| 92Excellent quality (A+) · 92 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Ideogram 4 | FP16 | 57.3 GB | 26 s | Runs well |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at FP16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE-Image Turbo | FP16 | 26.4 GB | 3.3 s | Runs great |
| 76Great quality (A) · 76 of 100: how capable the model is at FP16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | HiDream-I1 Fast | FP16 | 64.4 GB | 10 s | Runs great |
| 84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Z-Image Turbo | FP16 | 22.7 GB | 2.6 s | Runs great |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Cosmos3-Super Text2Image (64B) | FP8 | 69.1 GB | 37 s | Runs well |
| 93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Fibo 2.0 Dev | FP16 | 27.7 GB | 23 s | Runs well |
| 82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.1 Krea [dev] | FP16 | 36.4 GB | 12 s | Runs great |
| 80Great quality (A) · 80 of 100: how capable the model is at FP16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | HiDream-I1 Dev | FP16 | 64.4 GB | 17 s | Runs well |
| 93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image 2.1 | FP16 | 57.0 GB | 61 s | Slow |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE-Image | FP16 | 34.0 GB | 23 s | Runs well |
| 82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | MOSS-Image SFT | FP16 | 29.3 GB | 14 s | Runs well |
| 78Great quality (A) · 78 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 4B | FP16 | 18.1 GB | 1.0 s | Runs great |
| 78Great quality (A) · 78 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. | FLUX.1 [dev] | FP8 | 19.6 GB | 11 s | Runs great |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image 2512 | FP16 | 63.8 GB | 1.5 min | Slow |
| 84Great quality (A) · 84 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. | HiDream-I1 Full | FP16 | 64.4 GB | 46 s | Slow |
| 88Excellent quality (A+) · 88 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. | Qwen-Image | FP16 | 63.8 GB | 1.5 min | Slow |
| 82Great quality (A) · 82 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. | Z-Image | FP16 | 22.7 GB | 17 s | Runs well |
| 82Great quality (A) · 82 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. | FLUX.1 Kontext [dev] | FP16 | 37.0 GB | 23 s | Runs well |
| 87Excellent quality (A+) · 87 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. | FireRed-Image-Edit 1.1 | FP16 | 61.2 GB | 82 s | Slow |
| 70Great quality (A) · 70 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. | FLUX.1 [schnell] | FP16 | 36.4 GB | 2.0 s | Runs great |
| 86Excellent quality (A+) · 86 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. | Qwen-Image-Edit 2511 | FP16 | 61.2 GB | 82 s | Slow |
| 74Great quality (A) · 74 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. | FLUX.1 Fill [dev] | FP8 | 19.6 GB | 12 s | Runs great |
| 78Great quality (A) · 78 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. | Chroma1-HD | FP16 | 30.0 GB | 20 s | Runs well |
| 72Great quality (A) · 72 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. | Iris-3B | FP16 | 17.3 GB | 16 s | Runs well |
| 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 | 33.9 GB | 18 s | Runs well |
| 62Good quality (B) · 62 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 Diffusion 3.5 Large Turbo | FP16 | 30.0 GB | 1.6 s | Runs great |
| 64Good quality (B) · 64 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 Large | FP8 | 16.3 GB | 10 s | Runs great |
| 62Good quality (B) · 62 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. | Lumina-Image 2.0 | FP16 | 12.7 GB | 7.2 s | Runs great |
| 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. | Kolors | FP16 | 19.8 GB | 4.1 s | Runs great |
| 62Good quality (B) · 62 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. | Juggernaut XL v9 | FP16 | 8.9 GB | 4.6 s | Runs great |
| 62Good quality (B) · 62 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. | RealVisXL V5.0 | FP16 | 8.9 GB | 4.6 s | Runs great |
| 60Good quality (B) · 60 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. | Animagine XL 4.0 | FP16 | 8.9 GB | 4.3 s | Runs great |
| 60Good quality (B) · 60 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. | Illustrious XL v0.1 | FP16 | 8.9 GB | 4.3 s | Runs great |
| 60Good quality (B) · 60 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. | Playground v2.5 | FP16 | 8.9 GB | 7.7 s | Runs great |
| 58Good quality (B) · 58 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. | Stable Diffusion 3.5 Medium | FP16 | 18.4 GB | 6.1 s | Runs great |
| 64Good quality (B) · 64 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. | OmniGen2 | FP8 | 10.3 GB | 15 s | Runs well |
| 58Good quality (B) · 58 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. | DreamShaper XL v2 Turbo | FP16 | 8.9 GB | 1.3 s | Runs great |
| 58Good quality (B) · 58 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. | Pony Diffusion V6 XL | FP16 | 8.9 GB | 3.9 s | Runs great |
| 56Good quality (B) · 56 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. | Animagine XL 3.1 | FP16 | 8.9 GB | 4.3 s | Runs great |
| 55Good quality (B) · 55 of 100: how capable the model is at FP16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Stable Diffusion XL 1.0 | FP16 | 8.9 GB | 4.6 s | Runs great |
| 54Fair quality (C) · 54 of 100: how capable the model is at FP16, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | SDXL-Lightning (4-step) | FP16 | 8.9 GB | 0.7 s | Runs great |
| 52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Stable Diffusion 3 Medium | FP16 | 17.4 GB | 3.2 s | Runs great |
| 56Good quality (B) · 56 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. | AuraFlow v0.3 | FP8 | 10.4 GB | 13 s | Runs great |
| 52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Stable Cascade | FP16 | 14.0 GB | 5.1 s | Runs great |
| 52Fair quality (C) · 52 of 100: how capable the model is at FP16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Hunyuan-DiT v1.2 | FP16 | 9.3 GB | 6.1 s | Runs great |
| 48Fair quality (C) · 48 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. | Kandinsky 3 | FP16 | 25.9 GB | 9.2 s | Runs great |
| 50Fair quality (C) · 50 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. | PixArt-Σ XL 1024 | FP16 | 12.8 GB | 1.5 s | Runs great |
| 42Fair quality (C) · 42 of 100: how capable the model is at FP16, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | Realistic Vision V5.1 | FP16 | 2.8 GB | 1.2 s | Runs great |
| 40Fair quality (C) · 40 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. | SDXL Turbo | FP16 | 7.6 GB | 0.2 s | Runs great |
| 40Fair quality (C) · 40 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. | DreamShaper 8 | FP16 | 2.8 GB | 1.2 s | Runs great |
| 35Basic quality (D) · 35 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. | Stable Diffusion 1.5 | FP16 | 2.8 GB | 1.2 s | Runs great |
| 30Basic quality (D) · 30 of 100: how capable the model is at FP16, whatever it runs on. Match score 53/100 (quality, fit, speed and memory use) sets the ranking. | LCM DreamShaper v7 | FP16 | 2.8 GB | 0.3 s | Runs great |
| 28Basic quality (D) · 28 of 100: how capable the model is at FP16, whatever it runs on. Match score 52/100 (quality, fit, speed and memory use) sets the ranking. | SD Turbo | FP16 | 3.3 GB | 0.1 s | Runs great |
Video models on the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.5 (22B, video + audio) | FP16 | 82.5 GB | 1.6 min | Runs great |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax H3 (33B, video + audio) | FP16 | 113 GB | 17.8 min | Slow |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Cosmos3-Super Image2Video (64B) | FP16 | 139 GB | 38.4 min | Slow |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.3 | FP16 | 75.4 GB | 6.8 min | Runs well |
| 82Great quality (A) · 82 of 100: how capable the model is at FP16, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2 (19B, video + audio) | FP16 | 75.4 GB | 6.8 min | Runs well |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at FP16, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Kandinsky 6.0 Pro (29B, video + audio) | FP16 | 85.4 GB | 50.2 min | Very slow |
| 68Good quality (B) · 68 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. | LTX-Video 13B 0.9.8 (distilled) | FP16 | 47.9 GB | 61 s | Runs great |
| 86Excellent quality (A+) · 86 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. | Wan 2.2 I2V A14B | FP16 | 58.0 GB | 27.3 min | Slow |
| 86Excellent quality (A+) · 86 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. | Wan 2.2 T2V A14B | FP16 | 58.0 GB | 27.3 min | Slow |
| 74Great quality (A) · 74 of 100: how capable the model is at FP16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | FramePack I2V (HunyuanVideo 13B) | FP16 | 49.6 GB | 6.8 min | Runs well |
| 83Great quality (A) · 83 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. | Bernini-R A14B (video generation + editing) | FP8 | 26.0 GB | 11.1 min | Runs well |
| 84Great quality (A) · 84 of 100: how capable the model is at FP16, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | HunyuanVideo 1.5 (8.3B) | FP16 | 55.2 GB | 30.7 min | Slow |
| 76Great quality (A) · 76 of 100: how capable the model is at FP16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | HY-OmniWeaving (8.3B, unified video) | FP16 | 41.9 GB | 9.0 min | Runs well |
| 80Great quality (A) · 80 of 100: how capable the model is at FP16, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | SCAIL-2 14B (character animation) | FP16 | 52.5 GB | 20.5 min | Slow |
| 78Great quality (A) · 78 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. | Wan 2.2 Animate 14B | FP16 | 65.2 GB | 32.4 min | Slow |
| 78Great quality (A) · 78 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. | Wan 2.1 VACE 14B | FP16 | 64.6 GB | 37.6 min | Slow |
| 76Great quality (A) · 76 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. | Wan 2.2 S2V 14B (speech to video) | FP16 | 50.4 GB | 17.1 min | Slow |
| 78Great quality (A) · 78 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. | Wan 2.1 I2V 14B 720P | FP16 | 59.3 GB | 34.1 min | Slow |
| 76Great quality (A) · 76 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. | Step-Video T2V (30B) | FP16 | 78.2 GB | 52.9 min | Very slow |
| 78Great quality (A) · 78 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. | Wan 2.1 T2V 14B | FP16 | 58.0 GB | 34.1 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 | 31.5 GB | 5.3 min | Runs well |
| 76Great quality (A) · 76 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. | Wan-Dancer 14B (music to dance) | FP16 | 77.0 GB | 75.1 min | Very slow |
| 74Great quality (A) · 74 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. | Wan 2.1 I2V 14B 480P | FP16 | 46.5 GB | 15.4 min | Slow |
| 70Great quality (A) · 70 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. | Wan 2.2 TI2V 5B | FP16 | 43.1 GB | 8.9 min | Runs well |
| 74Great quality (A) · 74 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. | SkyReels V2 T2V 14B 540P | FP16 | 49.0 GB | 23.9 min | Slow |
| 76Great quality (A) · 76 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. | SkyReels V2 T2V 14B 720P | FP8 | 41.1 GB | 36.9 min | Slow |
| 55Good quality (B) · 55 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. | CogVideoX 5B I2V | FP16 | 25.3 GB | 3.1 min | Runs great |
| 55Good quality (B) · 55 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. | CogVideoX 5B | FP16 | 24.1 GB | 3.1 min | Runs great |
| 70Great quality (A) · 70 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. | Cosmos-Predict2 14B Video2World | FP16 | 57.6 GB | 27.3 min | Slow |
| 56Good quality (B) · 56 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. | Cosmos-Predict2 2B Video2World | FP8 | 26.8 GB | 3.8 min | Runs great |
| 70Great quality (A) · 70 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. | HunyuanVideo 13B | FP8 | 43.7 GB | 36.9 min | Slow |
| 70Great quality (A) · 70 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. | HunyuanVideo I2V 13B | FP8 | 43.7 GB | 36.9 min | Slow |
| 60Good quality (B) · 60 of 100: how capable the model is at FP16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Cosmos 1.0 Diffusion 7B Text2World | FP16 | 48.2 GB | 9.4 min | Runs well |
| 70Great quality (A) · 70 of 100: how capable the model is at FP16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | Open-Sora 2.0 (11B) | FP16 | 43.8 GB | 51.2 min | Very slow |
| 50Fair quality (C) · 50 of 100: how capable the model is at FP16, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | LTX-Video 2B | FP16 | 17.5 GB | 26 s | Runs great |
| 53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.1 T2V 1.3B | FP8 | 12.8 GB | 3.7 min | Runs great |
| 53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.1 VACE 1.3B | FP8 | 13.7 GB | 4.0 min | Runs great |
| 60Good quality (B) · 60 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. | CogVideoX 1.5 5B | FP16 | 50.3 GB | 15.4 min | Slow |
| 62Good quality (B) · 62 of 100: how capable the model is at FP16, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Mochi 1 Preview (10B) | FP16 | 41.4 GB | 18.8 min | Slow |
| 45Fair quality (C) · 45 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. | CogVideoX 2B | FP16 | 17.5 GB | 61 s | Runs great |
| 50Fair quality (C) · 50 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 Diffusion Forcing 1.3B | FP8 | 16.7 GB | 4.6 min | Runs well |
| 52Fair quality (C) · 52 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. | Allegro (2.8B) | FP16 | 38.2 GB | 20.5 min | Slow |
| 35Basic quality (D) · 35 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. | AnimateDiff v3 (SD 1.5) | FP16 | 4.7 GB | 20 s | Runs great |
Decision models on the NVIDIA GB300 Grace Blackwell Ultra Desktop Superchip
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 90Excellent quality (A+) · 90 of 100: how capable the model is at F16, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 4B | F16 | 21.5 GB | 42 ms | Runs great |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at F16, whatever it runs on. Match score 95/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 8B | F16 | 29.9 GB | 81 ms | Runs great |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at F16, whatever it runs on. Match score 94/100 (quality, fit, speed and memory use) sets the ranking. | zerank-2 | F16 | 21.5 GB | 42 ms | Runs great |
| 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 | 14.6 GB | 9.6 ms | Runs great |
| 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. | Shieldstral 1.0 3B | F16 | 21.1 GB | 40 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. | Intern-Decision 4B | F16 | 22.3 GB | 26 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 | 14.6 GB | 9.6 ms | Runs great |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Skywork Reward V2 Llama 3.1 8B | Q8_0 | 10.4 GB | 149 ms | Runs well |
| 82Great quality (A) · 82 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. | d1 3B | F16 | 19.5 GB | 19 ms | Runs great |
| 82Great quality (A) · 82 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. | mxbai-rerank-large v2 | F16 | 16.3 GB | 18 ms | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | GLiDE 27B | Q8_0 | 34.8 GB | 130 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 | 8.6 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 | 6.7 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. | LemonDecider 4B | F16 | 10.8 GB | 29 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 | 14.6 GB | 9.6 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. | zerank-1 small | F16 | 16.9 GB | 20 ms | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3Guard Gen 8B | Q8_0 | 22.2 GB | 88 ms | Runs great |
| 78Great quality (A) · 78 of 100: how capable the model is at F16, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | BGE Reranker v2 Gemma | F16 | 18.3 GB | 28 ms | Runs great |
| 84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. | Skywork Reward V2 Qwen3 8B | Q8_0 | 10.5 GB | 150 ms | Runs well |
| 84Great quality (A) · 84 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. | Granite Guardian 4.1 8B | Q8_0 | 22.4 GB | 90 ms | Runs great |
| 84Great quality (A) · 84 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 3.1 Nemotron Safety Guard 8B v3 | F16 | 29.5 GB | 99 ms | Runs great |
| 84Great quality (A) · 84 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. | Qwen3Guard Gen 4B | F16 | 22.3 GB | 56 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 | 7.1 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 | 14.2 GB | 8.6 ms | Runs great |
| 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 | 6.2 ms | Runs great |
| 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 | 4.3 ms | Runs great |
| 80Great quality (A) · 80 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. | Granite Guardian 3.3 8B | Q8_0 | 22.2 GB | 88 ms | Runs great |
| 80Great quality (A) · 80 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. | WildGuard 7B | F16 | 28.0 GB | 90 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. | BGE Reranker v2 M3 | F16 | 1.9 GB | 10 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 | 6.4 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 | 9.4 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. | Skywork Reward V2 Qwen3 0.6B | F16 | 2.0 GB | 17 ms | Runs great |
| 76Great quality (A) · 76 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. | NuExtract 2.0 4B | F16 | 20.8 GB | 65 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. | GTE Reranker ModernBERT Base | F16 | 0.9 GB | 5.7 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 | 7.1 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 | 6.2 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. | GLiGuard 300M | F16 | 1.1 GB | 6.3 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 | 5.7 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 | 6.3 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 | 4.8 ms | Runs great |
| 74Great quality (A) · 74 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. | Qwen3Guard Gen 0.6B | F16 | 14.9 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. | GLiClass Base v3 | F16 | 1.0 GB | 5.1 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 | 6.0 ms | Runs great |
| 70Great quality (A) · 70 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. | NuExtract 2.0 2B | F16 | 17.7 GB | 40 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 | 5.0 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. | ShieldGemma 9B | F16 | 32.4 GB | 91 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 | 5.2 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 | 6.4 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 | 13 ms | Runs great |
| 68Good quality (B) · 68 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. | Llama Guard 3 8B | F16 | 29.5 GB | 99 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 | 5.8 ms | Runs great |
| 74Great quality (A) · 74 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. | Nemotron Content Safety Reasoning 4B | Q4_K_M | 16.1 GB | 121 ms | Runs great |
| 70Great quality (A) · 70 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. | DynaGuard 1.7B | Q8_0 | 15.6 GB | 95 ms | Runs great |
| 58Good quality (B) · 58 of 100: how capable the model is at F16, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | ShieldGemma 2B | F16 | 18.6 GB | 28 ms | Runs great |
| 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 | 5.6 ms | Runs great |
| 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 | 6.3 ms | Runs great |
| 66Good quality (B) · 66 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. | Llama Guard 4 12B | Q8_0 | 26.3 GB | 127 ms | Runs great |
| 66Good quality (B) · 66 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | ShieldGemma 27B | Q8_0 | 42.8 GB | 252 ms | Runs well |
| 78Great quality (A) · 78 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. | DynaGuard 8B | Q6_K | 20.2 GB | 293 ms | Runs well |
| 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 | 4.3 ms | Runs great |
| 79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | Selene 1 Mini 8B | Q6_K | 20.1 GB | 346 ms | Runs well |
| 56Good quality (B) · 56 of 100: how capable the model is at F16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | Llama Guard 3 1B | F16 | 16.3 GB | 22 ms | Runs great |
| 77Great quality (A) · 77 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | CompassJudger-2 7B | Q6_K | 19.6 GB | 328 ms | Runs well |
| 80Great quality (A) · 80 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | gpt-oss-safeguard 120B | MXFP4 | 79.9 GB | 675 ms | Slow |
| 83Great quality (A) · 83 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | CompassJudger-2 32B | Q5_K_M | 37.0 GB | 1.3 s | Slow |
| 76Great quality (A) · 76 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | gpt-oss-safeguard 20B | MXFP4 | 25.5 GB | 636 ms | Slow |
| 65Good quality (B) · 65 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | GLIDER | Q6_K | 17.1 GB | 167 ms | Runs well |
| 60Good quality (B) · 60 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. | Flow Judge v0.1 | Q4_K_M | 16.3 GB | 138 ms | Runs well |
| 67Good quality (B) · 67 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Prometheus 2 7B | Q6_K | 19.4 GB | 312 ms | Runs well |
| 74Great quality (A) · 74 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. | Prometheus 2 8x7B | Q8_0 | 63.0 GB | 1.2 s | Slow |
Upgrade picks
No consumer GPU in our catalog runs more LLMs well than your current setup.
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.