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 |
|---|---|---|---|---|---|
| ZhaoXin KX-U6580 | 8.0 GB | 5.2 GB | 43 GB/s | 96 of 622 | — |
| ZhaoXin KX-U6580 · upgraded to the maker's maximum | 64.0 GB | 54.4 GB | 43 GB/s | 107 of 622 | — |
Specifications 64.0 GB configuration
| Maker | QNAP |
|---|---|
| Type | NAS |
| Processor | ZhaoXin KX-U6580 NAS (64 GB) · upgraded to the maker's maximum |
| Memory (RAM) | 64.0 GB |
| Usable for AI models | 54.4 GB |
| Memory bandwidth | 43 GB/s |
| FP16 compute | 0.1 TFLOPS |
| Runs models on | CPU cores |
| Drive bays | 6 x 3.5-inch SATA 6Gb/s, 3Gb/s + M.2: 2 x M.2 2280 PCIe Gen 3 x1 or SATA 6Gb/s slots |
| NAS system | QTS |
| Containers (Docker) | Yes |
| Virtual machines | Yes |
| Memory upgrade | SODIMM DDR4 · 2 slots · up to 64.0 GB per the maker |
| Graphics card options | PCIe: 2 Slot 1: PCIe Gen 3 x4 Slot 2: PCIe Gen 3 x4. |
| Notes | ZhaoXin KX-U6580 8-core 2.5GHz processor. Zhaoxin KX-U6580 x86 CPU (8C) with up to 64 GB RAM; Docker available, but CPU performance and GPU support for this platform are unverified, so expect small models only. |
| Product page | www.qnap.com (opens in a new tab) |
Running AI on the QNAP TVS-675
It can, with limits: expect small models only, at modest speed. Models run on its CPU cores, and this configuration leaves about 54.4 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 | In a container (Docker) |
| Ollama / Open WebUI or any other LLM server image | In a container (Docker) |
| Any Linux VM running an LLM runtime | In a virtual machine |
AI features from QNAP
| Feature | What it does | Where the AI runs |
|---|---|---|
| Qsirch RAG Search (cloud LLM mode) | Natural-language search and Q&A over NAS files; retrieval runs on the NAS but the LLM is a cloud API (Gemini, OpenAI, Azure OpenAI or OpenAI-compatible). | Cloud service or another computer |
Best LLMs for the QNAP TVS-675 64.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 92Excellent quality (A+) · 92 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. | Qwen3.6 35B-A3B | Q6_K | 34.6 GB | 4.1 tok/s | Slow |
| 92Excellent quality (A+) · 92 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. | Qwen3.5 35B-A3B | Q6_K | 34.6 GB | 4.1 tok/s | Slow |
| 92Excellent quality (A+) · 92 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. | MiniCPM-V 4.7 35B-A3B | Q6_K | 34.0 GB | 4.1 tok/s | Slow |
| 91Excellent quality (A+) · 91 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. | Nex N2 Mini (35B-A3B) | Q6_K | 33.9 GB | 4.1 tok/s | Slow |
| 90Excellent quality (A+) · 90 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. | Sage-A1.5 35B-A3B | Q6_K | 34.6 GB | 4.1 tok/s | Slow |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.5 35B-A3B | Q6_K | 34.6 GB | 4.1 tok/s | Slow |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | KAT-Coder V2.5 Dev (35B-A3B) | Q6_K | 33.5 GB | 4.1 tok/s | Slow |
| 95Excellent quality (A+) · 95 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. | Nanbeige4.3 33B | Q8_0 | 41.8 GB | 0.3 tok/s | Very slow |
| 95Excellent quality (A+) · 95 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. | Qwen3.8 27B | Q8_0 | 34.9 GB | 0.3 tok/s | Very slow |
| 88Excellent quality (A+) · 88 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking. | Apodex 1.1 Mini (35B-A3B) | Q6_K | 34.6 GB | 4.1 tok/s | Slow |
Best Image models for the QNAP TVS-675 64.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 92Excellent quality (A+) · 92 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. | Krea 2 Turbo | FP16 | 37.4 GB | 17.7 min | Very slow |
| 92Excellent quality (A+) · 92 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. | Qwen-Image 2.1 | Q8 GGUF | 41.6 GB | 4.7 h | Very slow |
| 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. | Qwen-Image 2512 | Q8 GGUF | 36.5 GB | 7.1 h | Very slow |
| 84Great quality (A) · 84 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. | FLUX.2 [klein] 9B | FP16 | 37.1 GB | 7.4 min | Very slow |
| 88Excellent quality (A+) · 88 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. | ERNIE-Image | FP16 | 34.0 GB | 1.5 h | Very slow |
| 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 | 1.5 h | Very slow |
Best Video models for the QNAP TVS-675 64.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 85Excellent quality (A+) · 85 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.3 | Q8 GGUF | 45.6 GB | 31.5 h | Very slow |
| 85Excellent quality (A+) · 85 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. | Bernini-R A14B (video generation + editing) | FP16 | 46.0 GB | 49.3 h | Very slow |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.2 I2V A14B | Q8 GGUF | 39.3 GB | 126.0 h | Very slow |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.2 T2V A14B | Q8 GGUF | 39.3 GB | 126.0 h | Very slow |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.5 (22B, video + audio) | Q8 GGUF | 49.8 GB | 7.2 h | Very slowtight fit |
Best Decision models for the QNAP TVS-675 64.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 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 | 9.5 GB | 82.8 s | Very 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. | Qwen3 Reranker 8B | Q8_0 | 13.9 GB | 168.6 s | Very 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 | 333.9 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 | 9.5 GB | 82.8 s | Very slow |
| 86Excellent quality (A+) · 86 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 v3.5 | Q8_0 | 5.8 GB | 12.4 s | Very slow |
| 78Great quality (A) · 78 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. | OpenAI Privacy Filter | Q8_0 | 2.4 GB | 561 ms | Slow |
| 86Excellent quality (A+) · 86 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. | Shieldstral 1.0 3B | Q8_0 | 9.3 GB | 79.3 s | Very slow |
| 84Great quality (A) · 84 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. | Jina Reranker v3 | Q8_0 | 5.8 GB | 12.4 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.