Products · QNAP · NAS
QNAP TBS-464
- Processor
- Intel Celeron N5105 / N5095
- Memory (RAM)
- 8 GB
- Released
- 2021
Specifications
| Maker | QNAP |
|---|---|
| Type | NAS |
| Processor | Intel Celeron N5105 / N5095 NAS (8 GB) |
| Memory (RAM) | 8.0 GB |
| Usable for AI models | 5.2 GB |
| Memory bandwidth | 24 GB/s |
| FP16 compute | 0.1 TFLOPS |
| Runs models on | CPU cores |
| Drive bays | M.2: 4 x M.2 2280 NVMe Gen3 x2 slots |
| NAS system | QTS |
| Containers (Docker) | Yes |
| Virtual machines | Yes |
| Memory upgrade | DDR4 soldered (non-expandable) · up to 8.0 GB per the maker |
| Notes | Intel Celeron N5105 4-core/4-thread processor, burst up to 2.9 GHz. Low-power x86 CPU with at most 8 GB RAM: only small (1-4B) quantized models on CPU via Docker. |
| Product page | www.qnap.com (opens in a new tab) |
Running AI on the QNAP TBS-464
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.
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 TBS-464
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 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. | Nemotron Labs Dory 1.0 4B | Q4_K_M | 3.9 GB | 3.0 tok/s | Slow |
| 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. | Gemma 4 E2B | Q4_K_M | 4.2 GB | 5.2 tok/s | Slow |
| 59Good quality (B) · 59 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 71/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM5 2B | Q6_K | 3.4 GB | 3.3 tok/s | Slow |
| 58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Nemotron 3.5 Bolt E4B | Q3_K_M | 5.1 GB | 3.5 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 69/100 (quality, fit, speed and memory use) sets the ranking. | Ling 3.0 Tiny (8B-A1.3B) | Q3_K_M | 5.1 GB | 11.5 tok/s | Runs welltight fit |
| 55Good quality (B) · 55 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Spark-X2.6 4B | Q3_K_M | 3.3 GB | 3.8 tok/s | Slow |
| 57Good quality (B) · 57 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Nanbeige4.2 3B | Q3_K_M | 4.5 GB | 3.7 tok/s | Slowtight fit |
| 57Good quality (B) · 57 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 E4B | Q3_K_M | 5.1 GB | 3.5 tok/s | Slowtight fit |
| 41Fair quality (C) · 41 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 69/100 (quality, fit, speed and memory use) sets the ranking. | Unlimited OCR 2 (3B-A0.6B) | Q4_K_M | 3.6 GB | 18.8 tok/s | Runs well |
| 52Fair quality (C) · 52 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 4B | Q3_K_M | 3.6 GB | 3.3 tok/s | Slow |
Best Image models for the QNAP TBS-464
| 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 | 57.8 min | Very slowCPU offload |
| 72Great quality (A) · 72 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 67/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 4B | Q4 GGUF | 4.6 GB | 8.5 min | Very slowtight fit · encoder unloaded after use |
| 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 | 19.8 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 | 3.9 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 | 2.4 h | Very slowCPU offload |
| 39Basic quality (D) · 39 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. | SDXL Turbo | FP8 | 4.2 GB | 55 s | Slow |
Best Video models for the QNAP TBS-464
| 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 55/100 (quality, fit, speed and memory use) sets the ranking. | AnimateDiff v3 (SD 1.5) | FP16 | 4.7 GB | 2.3 h | Very slowtight fit |
| 49Fair quality (C) · 49 of 100: how capable the model is at FP8, whatever it runs on. Match score 50/100 (quality, fit, speed and memory use) sets the ranking. | LTX-Video 2B | FP8 | 4.0 GB | 3.3 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 | 7.9 h | Very slowtight fit · CPU offload |
Best Decision models for the QNAP TBS-464
| 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 79/100 (quality, fit, speed and memory use) sets the ranking. | Jina Reranker v3.5 | Q8_0 | 1.9 GB | 17.2 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 | 114.8 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 | 1.9 GB | 17.2 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 | 114.8 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 | 110.0 s | Very slow |
| 78Great quality (A) · 78 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. | OpenAI Privacy Filter | Q8_0 | 2.4 GB | 777 ms | Slow |
| 80Great quality (A) · 80 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. | GLiNER2.5 Decide | Q8_0 | 1.2 GB | 7.6 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 | 44.1 s | Very slow |
Other products with the Intel Celeron N5105 / N5095 NAS (8 GB)
AS6706TProduct page (opens in a new tab)
AS6706T v2Product page (opens in a new tab)
MetaBox Pro HS500 (HS500-PRO)Product page (opens in a new tab)
TS-264Product page (opens in a new tab)
TS-464Product page (opens in a new tab)
TS-664Product page (opens in a new tab)
TS-364Product page (opens in a new tab)
HS-264Product page (opens in a new tab)
TS-1264U-RPProduct page (opens in a new tab)
TS-464U-RPProduct page (opens in a new tab)
TS-464UProduct page (opens in a new tab)
TS-864eU-RPProduct page (opens in a new tab)
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.