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 8.0 GB configuration
| Maker | QNAP |
|---|---|
| Type | NAS |
| Processor | ZhaoXin KX-U6580 NAS (8 GB) |
| Memory (RAM) | 8.0 GB |
| Usable for AI models | 5.2 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 5.2 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 8.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 65Good quality (B) · 65 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron Labs Dory 1.0 4B | Q5_K_M | 4.3 GB | 3.8 tok/s | Slow |
| 64Good quality (B) · 64 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Spark-X2.6 4B | Q5_K_M | 4.2 GB | 3.7 tok/s | Slow |
| 64Good quality (B) · 64 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 73/100 (quality, fit, speed and memory use) sets the ranking. | Nanbeige4.2 3B | Q4_K_M | 5.0 GB | 4.4 tok/s | Slowtight fit |
| 50Fair quality (C) · 50 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Ling 3.0 Tiny (8B-A1.3B) | Q3_K_M | 5.1 GB | 17.1 tok/s | Runs welltight fit |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Unlimited OCR 2 (3B-A0.6B) | Q4_K_M | 3.6 GB | 27.5 tok/s | Runs well |
| 58Good quality (B) · 58 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 4B | Q4_K_M | 4.1 GB | 3.9 tok/s | Slow |
| 59Good quality (B) · 59 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | TMax 4B | Q5_K_M | 4.3 GB | 3.6 tok/s | Slow |
| 52Fair quality (C) · 52 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 E2B | Q3_K_M | 3.6 GB | 10.2 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 70/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3.5 Bolt E4B | Q3_K_M | 5.1 GB | 5.2 tok/s | Slowtight fit |
| 57Good quality (B) · 57 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 70/100 (quality, fit, speed and memory use) sets the ranking. | Agents-A1 4B | Q4_K_M | 4.1 GB | 4.0 tok/s | Slow |
Best Image models for the QNAP TVS-675 8.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | FLUX 3 Image Klein | Q8 GGUF | 4.3 GB | 35.0 min | Very slowCPU offload |
| 72Great quality (A) · 72 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 68/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 4B | Q4 GGUF | 4.6 GB | 5.2 min | Very slowtight fit · encoder unloaded after use |
| 39Basic quality (D) · 39 of 100: how capable the model is at FP8, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | SDXL Turbo | FP8 | 4.2 GB | 33 s | Runs well |
| 82Great quality (A) · 82 of 100: how capable the model is at FP8, whatever it runs on. Match score 65/100 (quality, fit, speed and memory use) sets the ranking. | Z-Image Turbo | FP8 | 4.4 GB | 12.0 min | Very slowCPU offload |
| 81Great quality (A) · 81 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE-Image | Q4 GGUF | 4.1 GB | 2.4 h | Very slowCPU offload |
| 81Great quality (A) · 81 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | MOSS-Image SFT | Q8 GGUF | 4.1 GB | 86.0 min | Very slowCPU offload |
Best Video models for the QNAP TVS-675 8.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | AnimateDiff v3 (SD 1.5) | FP16 | 4.7 GB | 82.2 min | Very slowtight fit |
| 49Fair quality (C) · 49 of 100: how capable the model is at FP8, whatever it runs on. Match score 51/100 (quality, fit, speed and memory use) sets the ranking. | LTX-Video 2B | FP8 | 4.0 GB | 2.0 h | Very slowCPU offload |
| 44Fair quality (C) · 44 of 100: how capable the model is at FP8, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | CogVideoX 2B | FP8 | 4.7 GB | 4.8 h | Very slowtight fit · CPU offload |
Best Decision models for the QNAP TVS-675 8.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 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 | 1.9 GB | 12.4 s | Very slow |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 4B | Q5_K_M | 4.2 GB | 82.6 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 |
| 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 | 1.9 GB | 12.4 s | Very slow |
| 85Excellent quality (A+) · 85 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. | zerank-2 | Q5_K_M | 4.2 GB | 82.6 s | Very slow |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Shieldstral 1.0 3B | Q6_K | 4.4 GB | 79.2 s | Very slow |
| 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | GLiNER2.5 Decide | Q8_0 | 1.2 GB | 5.5 s | Very slow |
| 82Great quality (A) · 82 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | mxbai-rerank-large v2 | Q8_0 | 2.7 GB | 31.7 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.