
Products · Minisforum · NAS
Minisforum AI NAS N5 AIR-7640
- Processor
- AMD Ryzen 5 7640HS
- Memory (RAM)
- 16 or 96 GB
- Launch price
- $495
- Released
- 2026
Configurations
Pick one to see which models it runs. More memory lets larger models fit; bandwidth sets how fast they answer.
| Configuration | Memory | Usable for AI | Bandwidth | LLMs that run well | Launch price |
|---|---|---|---|---|---|
| AMD Ryzen 5 7640HS | 16.0 GB | 12.0 GB | 90 GB/s | 312 of 622 | $495 |
| AMD Ryzen 5 7640HS · upgraded to the maker's maximum | 96.0 GB | 83.5 GB | 90 GB/s | 364 of 622 | — |
Specifications 96.0 GB configuration
| Maker | Minisforum |
|---|---|
| Type | NAS |
| Processor | AMD Ryzen 5 7640HS NAS (96 GB) · upgraded to the maker's maximum |
| Memory (RAM) | 96.0 GB |
| Usable for AI models | 83.5 GB |
| Memory bandwidth | 90 GB/s |
| FP16 compute | 0.6 TFLOPS |
| Runs models on | CPU cores |
| Drive bays | 5x 3.5/2.5in SATA (30TB each, 150TB) + 3x M.2 NVMe |
| NAS system | MinisCloud OS |
| Containers (Docker) | Yes |
| Virtual machines | Yes |
| Memory upgrade | DDR5 SO-DIMM, 4800 or 5600 MT/s (non-ECC; AMD lists ECC 'No' for this… · 2 slots · up to 96.0 GB per the maker · non-ECC |
| Graphics card options | PCIe: 1x internal PCIe x16 slot, PCIe 4.0 x4 electrical. External GPU: 1x OCuLink port (rear); 2x USB4. |
| Notes | AMD Ryzen 5 7640HS. 6-core Zen 4 with Radeon 760M and up to 96GB dual-channel DDR5, Docker or a replacement OS. Small models at CPU speeds; add a GPU through the PCIe slot or OCuLink for more. |
| Product page | store.minisforum.com (opens in a new tab) |
Running AI on the Minisforum AI NAS N5 AIR-7640
It can, with limits: expect small models only, at modest speed. Models run on its CPU cores, and this configuration leaves about 83.5 GB for them after the NAS system and its storage services. The grades below assume the NAS isn’t busy with backups or media work at the same time. More memory is the upgrade that matters most: see the configurations.
Apps you can install to run models
| App | How it installs |
|---|---|
| Any Docker image | In a container (Docker) |
| Guest OS in the MinisCloud OS Virtual Machine app | In a virtual machine |
AI features from Minisforum
| Feature | What it does | Where the AI runs |
|---|---|---|
| MinisCloud AI Photo Library | Face recognition, scene sorting and image/semantic search over photos stored on the NAS (maker page wording). | On the NAS |
Best LLMs for the Minisforum AI NAS N5 AIR-7640 96.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 86Excellent quality (A+) · 86 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. | Kolibri 1 (78B-A3.5B) | Q4_K_M | 55.1 GB | 19.8 tok/s | Runs well |
| 81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Coder Next (80B-A3B) | Q4_K_M | 56.1 GB | 22.6 tok/s | Runs well |
| 81Great quality (A) · 81 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 88/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3-Next 80B-A3B Thinking | Q4_K_M | 57.1 GB | 22.6 tok/s | Runs well |
| 79Great quality (A) · 79 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Next 80B-A3B Instruct | Q4_K_M | 57.1 GB | 22.6 tok/s | Runs well |
| 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 | 74.2 GB | 14.6 tok/s | Runs welltight fit |
| 89Excellent quality (A+) · 89 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. | Nemotron 3.5 Super VL 120B-A12B | Q4_K_M | 83.3 GB | 6.0 tok/s | Slowtight fit |
| 85Excellent quality (A+) · 85 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. | Flint (40B-A2.5B) | Q4_K_M | 31.8 GB | 26.7 tok/s | Runs well |
| 88Excellent quality (A+) · 88 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. | Qwen3.6 35B-A3B | Q4_K_M | 29.4 GB | 22.6 tok/s | Runs well |
| 88Excellent quality (A+) · 88 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. | MiniCPM-V 4.7 35B-A3B | Q4_K_M | 28.9 GB | 22.6 tok/s | Runs well |
| 88Excellent quality (A+) · 88 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. | Qwen3.5 35B-A3B | Q4_K_M | 29.4 GB | 22.6 tok/s | Runs well |
Best Image models for the Minisforum AI NAS N5 AIR-7640 96.0 GB
| 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 82/100 (quality, fit, speed and memory use) sets the ranking. | Qwen-Image 2.1 | FP16 | 57.0 GB | 64.4 min | Very slow |
| 92Excellent quality (A+) · 92 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. | Ideogram 4 | FP16 | 57.3 GB | 26.8 min | Very slow |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [dev] | Q8 GGUF | 61.9 GB | 44.4 min | Very slow |
| 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. | Cosmos3-Super Text2Image (64B) | FP8 | 69.1 GB | 38.6 min | Very slow |
| 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. | Qwen-Image 2512 | FP16 | 63.8 GB | 1.6 h | Very slow |
| 91Excellent quality (A+) · 91 of 100: how capable the model is at FP8, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax H3 Image | FP8 | 72.0 GB | 9.7 min | Very slowtight fit |
Best Video models for the Minisforum AI NAS N5 AIR-7640 96.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | MiniMax H3 (33B, video + audio) | Q8 GGUF | 68.2 GB | 21.4 h | Very slow |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.5 (22B, video + audio) | Q8 GGUF | 49.8 GB | 1.9 h | Very slow |
| 86Excellent quality (A+) · 86 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. | Wan 2.2 I2V A14B | FP16 | 58.0 GB | 28.6 h | Very slow |
| 86Excellent quality (A+) · 86 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. | Wan 2.2 T2V A14B | FP16 | 58.0 GB | 28.6 h | Very slow |
| 84Great quality (A) · 84 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. | HunyuanVideo 1.5 (8.3B) | FP16 | 55.2 GB | 32.2 h | Very slow |
Best Decision models for the Minisforum AI NAS N5 AIR-7640 96.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 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 | 65 ms | Runs great |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3.5 | Q8_0 | 8.2 GB | 1.2 s | Slow |
| 68Good quality (B) · 68 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. | Llama Prompt Guard 2 22M | Q8_0 | 0.7 GB | 154 ms | Runs well |
| 80Great quality (A) · 80 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. | GLiNER2.5 Decide | Q8_0 | 1.2 GB | 520 ms | Slow |
| 90Excellent quality (A+) · 90 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. | Qwen3 Reranker 4B | Q8_0 | 11.8 GB | 7.9 s | Very slow |
| 84Great quality (A) · 84 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. | Jina Reranker v3 | Q8_0 | 8.2 GB | 1.2 s | Slow |
| 90Excellent quality (A+) · 90 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. | Qwen3 Reranker 8B | Q8_0 | 16.3 GB | 16.1 s | Very slow |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Skywork Reward V2 Llama 3.1 8B | Q8_0 | 10.4 GB | 31.6 s | Very slow |
Spec sources
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.