Hardware · Intel
What AI models can the Intel Core Ultra 7 255H / 9 285H NAS (32 GB) run?
- Unified memory
- 32.0 GB
- Usable for models
- 18.2 GB
- Memory bandwidth
- 102 GB/s
- Runs models on
- GPU (Vulkan)
- Released
- 2025
A NAS with this chip can run models on its GPU (Vulkan), sharing system memory with the NAS. We plan around 18.2 GB for models, what is left after the NAS system and its storage services. Models run in a container (Docker) or the maker’s app store, and speeds assume the NAS isn’t busy with storage work.
More about this hardware
| Maker | Intel |
|---|---|
| Type | NAS (network attached storage) processor |
| GPU share of memory | 57% (what the GPU can typically be given for a model) |
| Chip | Intel Core Ultra 7 255H / 9 285H |
| AI accelerator | Intel Arc 140T integrated graphics, sharing system memory. |
| NAS models with this chip | Topton N25 14-bay dual-10GbE NAS motherboard (Core Ultra 5 225H / 7 255H / 9 285H) · UGREEN NASync iDX6011 Pro |
| Memory type | System RAM, shared with the NAS operating system and its storage services |
| Bandwidth figure | 102.4 GB/s, estimated, see the note below |
| Note | One profile for every NAS built on this chip. Memory speed is an estimate from the chip’s supported memory in a typical NAS fitting; a unit with one memory module runs slower than one with two. Speed assumes the NAS is not busy with storage work. |
| Specifications | www.toptonpc.com |
Apps that run models well on the Intel Core Ultra 7 255H / 9 285H NAS (32 GB)
1 product with the Intel Core Ultra 7 255H / 9 285H NAS (32 GB)
Best LLMs for the Intel Core Ultra 7 255H / 9 285H NAS (32 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 26B-A4B | Q4_K_M | 18.2 GB | 29.0 tok/s | Runs welltight fit |
| 73Great quality (A) · 73 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | GLM-4.7 Flash (30B-A3B) | Q3_K_M | 17.8 GB | 45.0 tok/s | Runs welltight fit |
| 71Great quality (A) · 71 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | Hunyuan Hy-Memory 30B-A3B | Q3_K_M | 17.6 GB | 45.0 tok/s | Runs welltight fit |
| 73Great quality (A) · 73 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | Raon-1 mini Preview (30B-A4B) | Q3_K_M | 16.2 GB | 32.8 tok/s | Runs welltight fit |
| 70Great quality (A) · 70 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking. | LFM2.5 24B-A2B | Q4_K_M | 16.8 GB | 42.7 tok/s | Runs welltight fit |
| 70Great quality (A) · 70 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | gpt-oss 20B | MXFP4 | 14.2 GB | 32.4 tok/s | Runs great |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Maple Preview (20B-A1B) | Q4_K_M | 14.5 GB | 64.3 tok/s | Runs great |
| 74Great quality (A) · 74 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | DiffusionGemma 26B-A4B IT | Q4_K_M | 18.2 GB | 27.7 tok/s | Runs welltight fit |
| 67Good quality (B) · 67 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | North Mini Code 1.0 (30B-A3B) | Q3_K_M | 17.3 GB | 45.0 tok/s | Runs welltight fit |
| 67Good quality (B) · 67 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron Cascade 2 30B-A3B | Q3_K_M | 17.6 GB | 39.4 tok/s | Runs welltight fit |
| 65Good quality (B) · 65 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 30B-A3B Thinking 2507 | Q3_K_M | 17.8 GB | 41.4 tok/s | Runs welltight fit |
| 65Good quality (B) · 65 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Coder 30B-A3B | Q3_K_M | 17.8 GB | 41.4 tok/s | Runs welltight fit |
Best Image models for the Intel Core Ultra 7 255H / 9 285H NAS (32 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | Z-Image Turbo | FP8 | 12.6 GB | 21 s | Runs well |
| 76Great quality (A) · 76 of 100: how capable the model is at FP8, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 4B | FP8 | 10.2 GB | 8.4 s | Runs great |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at FP8, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | FLUX 3 Image Klein | FP8 | 12.4 GB | 48 s | Slow |
| 83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE-Image Turbo | FP8 | 14.5 GB | 27 s | Runs well |
| 82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 9B | FP8 | 11.7 GB | 16 s | Runs wellencoder unloaded after use |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at FP8, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Krea 2 Turbo | FP8 | 15.7 GB | 38 s | Runs welltight fit · encoder unloaded after use |
Best Video models for the Intel Core Ultra 7 255H / 9 285H NAS (32 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 49Fair quality (C) · 49 of 100: how capable the model is at FP8, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | LTX-Video 2B | FP8 | 10.8 GB | 3.5 min | Runs great |
| 74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | HY-OmniWeaving (8.3B, unified video) | FP8 | 15.7 GB | 77.9 min | Very slowtight fit · encoder unloaded after use |
| 53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | CogVideoX 5B | FP8 | 14.3 GB | 25.2 min | Slow |
| 53Fair quality (C) · 53 of 100: how capable the model is at FP8, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | CogVideoX 5B I2V | FP8 | 14.9 GB | 25.2 min | Slow |
| 68Good quality (B) · 68 of 100: how capable the model is at FP16, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Kandinsky 6.0 Video Lite (3B, video + audio) | FP16 | 14.7 GB | 50.6 min | Very slowencoder unloaded after use |
Best Decision models for the Intel Core Ultra 7 255H / 9 285H NAS (32 GB)
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 86Excellent quality (A+) · 86 of 100: how capable the model is at F16, whatever it runs on. Match score 93/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3.5 | F16 | 3.5 GB | 73 ms | Runs great |
| 84Great quality (A) · 84 of 100: how capable the model is at F16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3 | F16 | 3.5 GB | 73 ms | Runs great |
| 80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | FRIDA-Decisions | F16 | 2.4 GB | 45 ms | Runs great |
| 80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | GLiNER2.5 Decide | F16 | 1.7 GB | 28 ms | Runs great |
| 80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 0.6B | F16 | 3.5 GB | 73 ms | Runs great |
| 76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | Llama Prompt Guard 2 86M | F16 | 1.2 GB | 32 ms | Runs great |
| 76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | mxbai-rerank-base v2 | F16 | 3.1 GB | 60 ms | Runs great |
| 82Great quality (A) · 82 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. | mxbai-rerank-large v2 | Q8_0 | 3.8 GB | 151 ms | Runs well |
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.