Specifications
| Maker | QNAP |
|---|---|
| Type | NAS |
| Processor | Rockchip RK3568 NAS (4 GB) |
| Memory (RAM) | 4.0 GB |
| Usable for AI models | 2.0 GB |
| Memory bandwidth | 13 GB/s |
| FP16 compute | 0.1 TFLOPS |
| Runs models on | CPU cores |
| Drive bays | 4 x 3.5-inch SATA 6Gb/s, 3Gb/s |
| NAS system | QTS |
| Containers (Docker) | Yes |
| Virtual machines | No |
| Memory upgrade | up to 4.0 GB per the maker |
| Notes | ARM 4-core Cortex-A55 2.0GHz processor. ARM Cortex-A55 quad-core with 4 GB soldered RAM (not expandable) and an NPU used for QNAP image recognition. Container Station is supported, but 4 GB and a low-power ARM CPU leave room only for tiny (about 1B) models, and QNAP's Ollama tutorial says only a few ARM models are supported. No PCIe slot. |
| Product page | www.qnap.com (opens in a new tab) |
Running AI on the QNAP TS-433eU
It can, with limits: expect small models only, at modest speed. Models run on its CPU cores, and this configuration leaves about 2.0 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.
Apps you can install to run models
| App | How it installs |
|---|---|
| Ollama | In a container (Docker) |
| Open WebUI | In a container (Docker) |
AI features from QNAP
| Feature | What it does | Where the AI runs |
|---|---|---|
| QuMagie + QNAP AI Core | Photo management with on-device face, object and scene recognition (QNAP AI Core image-recognition engine). | On the NAS |
| Qsirch RAG Search (cloud LLM mode) | Chat with NAS files using a cloud LLM (Gemini, OpenAI, Azure OpenAI or OpenAI-compatible API); the model runs remotely. | Cloud service or another computer |
| AI Service Center (beta) cloud models | Central hub for connecting NAS apps to cloud models (OpenAI, Azure OpenAI, Gemini, Claude, OpenAI-compatible); local model library is limited to x86 NAS with a tested GPU (third-party report). | Cloud service or another computer |
Best LLMs for the QNAP TS-433eU
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 47Fair quality (C) · 47 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 64/100 (quality, fit, speed and memory use) sets the ranking. | LFM3 1.7B | Q3_K_M | 1.7 GB | 3.3 tok/s | Slowtight fit |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | PaddleOCR-VL 1.6 0.9B | Q4_K_M | 1.5 GB | 4.5 tok/s | Slow |
| 39Basic quality (D) · 39 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-OCR 1.0 1.3B | Q4_K_M | 1.7 GB | 3.4 tok/s | Slow |
| 35Basic quality (D) · 35 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | LFM3-VL 2B | Q2_K | 1.6 GB | 3.7 tok/s | Slow |
| 34Basic quality (D) · 34 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM5 1B | Q4_K_M | 1.6 GB | 4.0 tok/s | Slow |
| 33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 59/100 (quality, fit, speed and memory use) sets the ranking. | MiniCPM-V 4.7 1B | Q3_K_M | 1.6 GB | 3.6 tok/s | Slow |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | LFM2.5 1.2B Instruct | Q4_K_M | 1.6 GB | 3.7 tok/s | Slow |
| 33Basic quality (D) · 33 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking. | TMax 2B | Q3_K_M | 1.8 GB | 3.0 tok/s | Slowtight fit |
| 30Basic quality (D) · 30 of 100: how capable the model is at Q2_K, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | LFM2.5 2.6B | Q2_K | 2.0 GB | 2.7 tok/s | Very slowtight fit |
| 24Basic quality (D) · 24 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 56/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 0.8B | Q4_K_M | 1.4 GB | 5.0 tok/s | Slow |
Best Image models for the QNAP TS-433eU
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 39Basic quality (D) · 39 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. | SDXL Turbo | FP8 | 1.6 GB | 63 s | SlowCPU offload |
| 42Fair quality (C) · 42 of 100: how capable the model is at FP16, whatever it runs on. Match score 47/100 (quality, fit, speed and memory use) sets the ranking. | Realistic Vision V5.1 | FP16 | 1.3 GB | 9.4 min | Very slowCPU offload |
| 28Basic quality (D) · 28 of 100: how capable the model is at FP16, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | SD Turbo | FP16 | 1.3 GB | 38 s | Runs wellCPU offload |
| 40Fair quality (C) · 40 of 100: how capable the model is at FP16, whatever it runs on. Match score 46/100 (quality, fit, speed and memory use) sets the ranking. | DreamShaper 8 | FP16 | 1.3 GB | 9.4 min | Very slowCPU offload |
| 30Basic quality (D) · 30 of 100: how capable the model is at FP16, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. | LCM DreamShaper v7 | FP16 | 1.3 GB | 2.0 min | SlowCPU offload |
| 35Basic quality (D) · 35 of 100: how capable the model is at FP16, whatever it runs on. Match score 44/100 (quality, fit, speed and memory use) sets the ranking. | Stable Diffusion 1.5 | FP16 | 1.3 GB | 9.4 min | Very slowCPU offload |
Best Video models for the QNAP TS-433eU
None of the video models in our catalog fit in this much memory.
Best Decision models for the QNAP TS-433eU
| 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 | 1.6 GB | 25.9 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 | 1.6 GB | 25.9 s | Very 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 | 11.4 s | Very 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. | FRIDA-Decisions | Q8_0 | 1.7 GB | 19.0 s | Very slow |
| 80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 0.6B | Q8_0 | 1.6 GB | 25.9 s | Very slow |
| 76Great quality (A) · 76 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | Llama Prompt Guard 2 86M | Q8_0 | 1.0 GB | 13.0 s | Very slow |
| 79Great quality (A) · 79 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | mxbai-rerank-large v2 | Q5_K_M | 1.9 GB | 66.1 s | Very slowtight fit |
| 76Great quality (A) · 76 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | mxbai-rerank-base v2 | Q8_0 | 1.3 GB | 21.1 s | Very slow |
Other products with the Rockchip RK3568 NAS (4 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.