Products · Asustor · NAS
Asustor FS6812X
- Processor
- AMD Ryzen Embedded V3C14
- Memory (RAM)
- 16 or 64 GB
- Launch price
- $1,399
- Released
- 2024
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 Embedded V3C14 | 16.0 GB | 12.0 GB | 38 GB/s | 175 of 622 | $1,399 |
| AMD Ryzen Embedded V3C14 · upgraded to the maker's maximum | 64.0 GB | 54.4 GB | 38 GB/s | 216 of 622 | — |
Specifications 16.0 GB configuration
| Maker | Asustor |
|---|---|
| Type | NAS |
| Processor | AMD Ryzen Embedded V3C14 NAS (16 GB) |
| Memory (RAM) | 16.0 GB |
| Usable for AI models | 12.0 GB |
| Memory bandwidth | 38 GB/s |
| FP16 compute | 0.2 TFLOPS |
| Runs models on | CPU cores |
| Drive bays | 12x M.2 NVMe (PCIe 4.0: 1x x4, 3x x2, 4x x1; PCIe 3.0: 1x x4, 1x x2, 2x x1) |
| NAS system | ADM 5.x |
| Containers (Docker) | Yes |
| Virtual machines | Yes |
| Memory upgrade | DDR5-4800 SO-DIMM (ECC shipped) · 2 slots · up to 64.0 GB per the maker · ECC |
| Notes | AMD Ryzen Embedded V3C14 (2.3-3.8 GHz). AMD Ryzen Embedded V3C14 (4C/8T Zen 3+) with up to 64 GB DDR5 gives room for 7-14B quantized models and larger ones slowly, but everything is CPU-only: the chip has no iGPU, the USB4 ports do not support eGPUs, and there is no PCIe slot. |
| Product page | www.asustor.com (opens in a new tab) |
Running AI on the Asustor FS6812X
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 | From the NAS app store |
| 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; App Central lists this model's series as supported, ADM 5.1.1+). | On the NAS |
Best LLMs for the Asustor FS6812X 16.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 78Great quality (A) · 78 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 12B | Q4_K_M | 9.5 GB | 3.3 tok/s | Slow |
| 79Great quality (A) · 79 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | K2 Horizon 7B | Q6_K | 10.1 GB | 3.0 tok/s | Slow |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Mellum2.1 Thinking (12B-A2.5B) | Q4_K_M | 9.1 GB | 14.9 tok/s | Runs well |
| 58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Maple Preview (20B-A1B) | Q3_K_M | 11.6 GB | 30.7 tok/s | Runs welltight fit |
| 75Great quality (A) · 75 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | MiMo V2.6 Distill Qwen 9B | Q5_K_M | 8.5 GB | 3.4 tok/s | Slow |
| 75Great quality (A) · 75 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | SenseNova Loop 9B Preview | Q5_K_M | 8.9 GB | 3.4 tok/s | Slow |
| 74Great quality (A) · 74 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.5 9B | Q5_K_M | 8.7 GB | 3.4 tok/s | Slow |
| 73Great quality (A) · 73 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 9B | Q5_K_M | 8.7 GB | 3.4 tok/s | Slow |
| 73Great quality (A) · 73 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. | TMax 9B | Q6_K | 9.2 GB | 3.0 tok/s | Slow |
| 72Great quality (A) · 72 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.0 9B | Q5_K_M | 8.7 GB | 3.4 tok/s | Slow |
Best Image models for the Asustor FS6812X 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 79/100 (quality, fit, speed and memory use) sets the ranking. | FLUX 3 Image Klein | Q4 GGUF | 10.2 GB | 15.7 min | Very slow |
| 76Great quality (A) · 76 of 100: how capable the model is at FP8, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 4B | FP8 | 10.2 GB | 2.1 min | Slow |
| 78Great quality (A) · 78 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | Z-Image Turbo | Q4 GGUF | 10.1 GB | 6.9 min | Very slow |
| 79Great quality (A) · 79 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. | ERNIE-Image Turbo | Q4 GGUF | 11.3 GB | 8.8 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 | 46.7 min | Very slow |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE-Image | Q8 GGUF | 11.2 GB | 60.8 min | Very slowtight fit · encoder unloaded after use |
Best Video models for the Asustor FS6812X 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 63/100 (quality, fit, speed and memory use) sets the ranking. | LTX-Video 2B | FP8 | 10.8 GB | 51.5 min | Very 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 | 32.2 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 | 23.7 h | Very slowCPU offload |
| 55Good quality (B) · 55 of 100: how capable the model is at FP16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.1 T2V 1.3B | FP16 | 8.4 GB | 9.6 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 60/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.1 VACE 1.3B | FP16 | 10.1 GB | 10.4 h | Very slowencoder unloaded after use |
Best Decision models for the Asustor FS6812X 16.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 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. | OpenAI Privacy Filter | Q8_0 | 2.4 GB | 120 ms | Runs great |
| 86Excellent quality (A+) · 86 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 v3.5 | Q8_0 | 2.4 GB | 2.6 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. | Qwen3 Reranker 4B | Q8_0 | 6.1 GB | 17.4 s | Very slow |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 8B | Q6_K | 8.6 GB | 35.2 s | Very slow |
| 84Great quality (A) · 84 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. | Jina Reranker v3 | Q8_0 | 2.4 GB | 2.6 s | Very slow |
| 88Excellent quality (A+) · 88 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. | zerank-2 | Q8_0 | 6.1 GB | 17.4 s | Very slow |
| 80Great quality (A) · 80 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. | GLiNER2.5 Decide | Q8_0 | 1.2 GB | 1.1 s | Slow |
| 90Excellent quality (A+) · 90 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. | Skywork Reward V2 Llama 3.1 8B | Q8_0 | 10.4 GB | 69.6 s | Very slowtight fit |
Other products with the AMD Ryzen Embedded V3C14 NAS (16 GB)
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.