Products · QNAP · NAS
QNAP TVS-951X
- Processor
- Intel Celeron J1800 / N3710 / 3865U
- Memory (RAM)
- 8 or 32 GB
- Released
- 2018
Product page (opens in a new tab)Discontinued Full AI report
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 |
|---|---|---|---|---|---|
| Intel Celeron J1800 / N3710 / 3865U | 8.0 GB | 5.2 GB | 13 GB/s | 18 of 622 | — |
| Intel Celeron J1800 / N3710 / 3865U · upgraded to the maker's maximum | 32.0 GB | 26.2 GB | 13 GB/s | 18 of 622 | — |
Specifications 32.0 GB configuration
| Maker | QNAP |
|---|---|
| Type | NAS |
| Processor | Intel Celeron J1800 / N3710 / 3865U NAS (32 GB) · upgraded to the maker's maximum |
| Memory (RAM) | 32.0 GB |
| Usable for AI models | 26.2 GB |
| Memory bandwidth | 13 GB/s |
| FP16 compute | 0.0 TFLOPS |
| Runs models on | CPU cores |
| Drive bays | 5 x 3.5-inch + 4 x 2.5-inch SATA 6Gb/s, 3Gb/s |
| NAS system | QTS |
| Containers (Docker) | Yes |
| Virtual machines | Yes |
| Memory upgrade | SODIMM DDR4 · 2 slots · up to 32.0 GB per the maker |
| Availability | Discontinued (sold used or refurbished) |
| Notes | Intel Celeron 3865U 2-core 1.8 GHz processor. x86-64 dual-core Celeron 3865U with up to 32 GB RAM: models fit in memory but two slow cores limit it to small quantized models on CPU. |
| Product page | www.qnap.com (opens in a new tab)Discontinued |
Running AI on the QNAP TVS-951X
It can, with limits: expect small models only, at modest speed. Models run on its CPU cores, and this configuration leaves about 26.2 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-951X 32.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 26B-A4B | Q5_K_M | 21.4 GB | 0.7 tok/s | Very slow |
| 94Excellent quality (A+) · 94 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.8 27B | Q6_K | 26.0 GB | 0.1 tok/s | Very slowtight fit |
| 93Excellent quality (A+) · 93 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. | Qwen3.6 27B | Q6_K | 26.0 GB | 0.1 tok/s | Very slowtight fit |
| 88Excellent quality (A+) · 88 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. | Qwen3.6 35B-A3B | Q4_K_M | 24.8 GB | 1.1 tok/s | Very slowtight fit |
| 88Excellent quality (A+) · 88 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. | MiniCPM-V 4.7 35B-A3B | Q4_K_M | 24.3 GB | 1.1 tok/s | Very slowtight fit |
| 88Excellent quality (A+) · 88 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. | Qwen3.5 35B-A3B | Q4_K_M | 24.8 GB | 1.1 tok/s | Very slowtight fit |
| 92Excellent quality (A+) · 92 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. | Qwen3.5 27B | Q6_K | 26.0 GB | 0.1 tok/s | Very slowtight fit |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Nex N2 Mini (35B-A3B) | Q4_K_M | 24.3 GB | 1.1 tok/s | Very slowtight fit |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Nanbeige4.3 33B | Q4_K_M | 24.6 GB | 0.1 tok/s | Very slowtight fit |
| 86Excellent quality (A+) · 86 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | KAT-Coder V2.5 Dev (35B-A3B) | Q4_K_M | 24.0 GB | 1.1 tok/s | Very slowtight fit |
Best Image models for the QNAP TVS-951X 32.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 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. | Krea 2 Turbo | FP8 | 20.2 GB | 44.1 min | Very slow |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE-Image | Q8 GGUF | 18.9 GB | 4.8 h | Very slow |
| 85Excellent quality (A+) · 85 of 100: how capable the model is at NF4, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Ideogram 4 | NF4 | 21.8 GB | 5.2 h | Very slow |
| 83Great quality (A) · 83 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. | FLUX.2 [klein] 9B | Q8 GGUF | 20.5 GB | 23.6 min | Very slow |
| 90Excellent quality (A+) · 90 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | FLUX 3 Image Klein | Q8 GGUF | 12.8 GB | 74.7 min | Very slow |
| 93Excellent quality (A+) · 93 of 100: how capable the model is at FP16, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | Fibo 2.0 Dev | FP16 | 18.9 GB | 4.5 h | Very slowencoder unloaded after use |
Best Video models for the QNAP TVS-951X 32.0 GB
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Bernini-R A14B (video generation + editing) | FP8 | 20.3 GB | 129.3 h | Very slowencoder unloaded after use |
| 70Great quality (A) · 70 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.2 S2V 14B (speech to video) | Q4 GGUF | 21.6 GB | 228.1 h | Very slow |
| 74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | HY-OmniWeaving (8.3B, unified video) | FP8 | 24.6 GB | 90.7 h | Very slowtight fit |
| 68Good quality (B) · 68 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.1 I2V 14B 480P | Q4 GGUF | 20.6 GB | 205.3 h | Very slow |
| 79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | LTX-2.3 | Q4 GGUF | 24.5 GB | 95.8 h | Very slowtight fit · encoder unloaded after use |
Best Decision models for the QNAP TVS-951X 32.0 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 80/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 4B | Q8_0 | 7.3 GB | 459.8 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 | 11.7 GB | 936.8 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. | Skywork Reward V2 Llama 3.1 8B | Q8_0 | 10.4 GB | 1,855.1 s | Very slow |
| 88Excellent quality (A+) · 88 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. | zerank-2 | Q8_0 | 7.3 GB | 459.8 s | Very 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. | Jina Reranker v3.5 | Q8_0 | 3.6 GB | 68.6 s | Very slow |
| 86Excellent quality (A+) · 86 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. | Shieldstral 1.0 3B | Q8_0 | 7.0 GB | 440.4 s | Very slow |
| 84Great quality (A) · 84 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. | Jina Reranker v3 | Q8_0 | 3.6 GB | 68.6 s | Very slow |
| 84Great quality (A) · 84 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. | Intern-Decision 4B | Q8_0 | 7.6 GB | 261.0 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.