Products · Asustor · NAS
Asustor Flashstor 12 Pro Gen3 (FS812X1)
- Processor
- AMD Ryzen 5 PRO 8640U
- Memory (RAM)
- 16 or 96 GB
- 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 PRO 8640U | 16.0 GB | 12.0 GB | 77 GB/s | 311 of 622 | — |
| AMD Ryzen 5 PRO 8640U · upgraded to the maker's maximum | 96.0 GB | 83.5 GB | 77 GB/s | 363 of 622 | — |
Specifications 16.0 GB configuration
| Maker | Asustor |
|---|---|
| Type | NAS |
| Processor | AMD Ryzen 5 PRO 8640U NAS (16 GB) |
| Memory (RAM) | 16.0 GB |
| Usable for AI models | 12.0 GB |
| Memory bandwidth | 77 GB/s |
| FP16 compute | 0.5 TFLOPS |
| Runs models on | CPU cores |
| Drive bays | 12x M.2 NVMe (PCIe 4.0: 1x x4, 4x x2, 2x x1; PCIe 3.0: 3x x2, 2x x1) |
| NAS system | ADM |
| Containers (Docker) | Yes |
| Virtual machines | Yes |
| Memory upgrade | DDR5-5600 SO-DIMM (ECC shipped) · 2 slots · up to 96.0 GB per the maker · ECC |
| Availability | Announced, not on general sale when checked |
| Notes | AMD Ryzen 5 PRO 8640U (3.5-4.9 GHz). Ryzen 5 PRO 8640U (6C/12T Zen 4) with Radeon 760M graphics, a Ryzen AI NPU and up to 96 GB DDR5 is the strongest AI hardware Asustor has shown. Announced or in crowdfunding; not on general sale when checked (November 2026). |
| Product page | www.asustor.com (opens in a new tab) |
Running AI on the Asustor Flashstor 12 Pro Gen3 (FS812X1)
Yes, it runs AI models on the NAS itself. Models run on its CPU cores, and this configuration leaves about 12.0 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 |
|---|---|
| Ollama / Open WebUI / other containers via Docker Engine + Portainer CE | In a container (Docker) |
AI features from Asustor
| Feature | What it does | Where the AI runs |
|---|---|---|
| Photo Gallery AI Search / Category Albums (beta, Photo Gallery 4.1) | Natural-language photo search and automatic category albums in Asustor's Photo Gallery app (beta since Photo Gallery 4.1.0). Asustor's Computex 2026 release says its AI features are optional and 'completely local'. | On the NAS |
Best LLMs for the Asustor Flashstor 12 Pro Gen3 (FS812X1) 16.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 66Good quality (B) · 66 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. | Mellum2.1 Thinking (12B-A2.5B) | Q4_K_M | 9.1 GB | 24.1 tok/s | Runs well |
| 78Great quality (A) · 78 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. | Gemma 4 12B | Q4_K_M | 9.5 GB | 5.5 tok/s | Slow |
| 58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Maple Preview (20B-A1B) | Q3_K_M | 11.6 GB | 48.0 tok/s | Runs welltight fit |
| 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Ling 3.0 Tiny (8B-A1.3B) | Q4_K_M | 6.6 GB | 43.1 tok/s | Runs great |
| 51Fair quality (C) · 51 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | LFM2.5 24B-A2B | Q2_K | 11.3 GB | 38.6 tok/s | Runs welltight fit |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3.5 Bolt E4B | Q4_K_M | 6.6 GB | 14.5 tok/s | Runs well |
| 49Fair quality (C) · 49 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Ling Mini 2.0 (16B-A1.4B) | Q4_K_M | 11.8 GB | 40.4 tok/s | Runs welltight fit |
| 64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 E4B | Q4_K_M | 6.6 GB | 14.5 tok/s | Runs well |
| 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | Kimi-VL A3B Thinking 2506 | Q4_K_M | 11.8 GB | 20.3 tok/s | Runs welltight fit |
| 49Fair quality (C) · 49 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. | LFM2.5 8B-A1B | Q4_K_M | 6.8 GB | 38.1 tok/s | Runs great |
Best Image models for the Asustor Flashstor 12 Pro Gen3 (FS812X1) 16.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 84Great quality (A) · 84 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | FLUX 3 Image Klein | Q4 GGUF | 10.2 GB | 8.5 min | Very slow |
| 76Great quality (A) · 76 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. | FLUX.2 [klein] 4B | FP8 | 10.2 GB | 67 s | Slow |
| 78Great quality (A) · 78 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Z-Image Turbo | Q4 GGUF | 10.1 GB | 3.7 min | Very slow |
| 79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE-Image Turbo | Q4 GGUF | 11.3 GB | 4.8 min | Very slowtight fit |
| 76Great quality (A) · 76 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | Z-Image | Q4 GGUF | 10.1 GB | 25.4 min | Very slow |
| 78Great quality (A) · 78 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 9B | Q4 GGUF | 8.0 GB | 2.8 min | Very slowencoder unloaded after use |
Best Video models for the Asustor Flashstor 12 Pro Gen3 (FS812X1) 16.0 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 64/100 (quality, fit, speed and memory use) sets the ranking. | LTX-Video 2B | FP8 | 10.8 GB | 28.1 min | Slowtight fit |
| 83Great quality (A) · 83 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. | Bernini-R A14B (video generation + editing) | FP8 | 10.7 GB | 17.5 h | Very slowtight fit · CPU offload |
| 74Great quality (A) · 74 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. | HY-OmniWeaving (8.3B, unified video) | FP8 | 7.8 GB | 12.9 h | Very slowCPU offload |
| 55Good quality (B) · 55 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. | Wan 2.1 T2V 1.3B | FP16 | 8.4 GB | 5.2 h | Very slowencoder unloaded after use |
| 55Good quality (B) · 55 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. | Wan 2.1 VACE 1.3B | FP16 | 10.1 GB | 5.7 h | Very slowencoder unloaded after use |
Best Decision models for the Asustor Flashstor 12 Pro Gen3 (FS812X1) 16.0 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 | 75 ms | Runs great |
| 86Excellent quality (A+) · 86 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 v3.5 | Q8_0 | 2.4 GB | 1.4 s | Very slow |
| 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 | 610 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 | 6.1 GB | 9.3 s | Very slow |
| 84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3 | Q8_0 | 2.4 GB | 1.4 s | Very slow |
| 68Good quality (B) · 68 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 Prompt Guard 2 22M | Q8_0 | 0.7 GB | 180 ms | Runs well |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 8B | Q6_K | 8.6 GB | 18.8 s | Very slow |
| 88Excellent quality (A+) · 88 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. | zerank-2 | Q8_0 | 6.1 GB | 9.3 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.