Products · Zettlab · NAS
Zettlab D4
- Processor
- Rockchip RK3588
- Memory (RAM)
- 16 GB
- Launch price
- $500
- Released
- 2025
Specifications
| Maker | Zettlab |
|---|---|
| Type | NAS |
| Processor | Rockchip RK3588 NAS (16 GB) |
| Memory (RAM) | 16.0 GB |
| Usable for AI models | 12.0 GB |
| Memory bandwidth | 34 GB/s |
| FP16 compute | 0.1 TFLOPS |
| Runs models on | CPU cores |
| Drive bays | 4x SATA + 1x M.2 NVMe |
| NAS system | ZettOS |
| Containers (Docker) | Yes |
| Virtual machines | Yes |
| Memory upgrade | LPDDR4x · up to 16.0 GB per the maker · non-ECC |
| Notes | Rockchip RK3588. The 6 TOPS NPU runs ZettAI search, categorising and transcription on the device, but the maker's own table says AI Q&A chat runs 'via PC Computing Power'; an LLM on the NAS itself would mean a small model in Docker on the ARM CPU with 16 GB of soldered RAM. |
| Product page | zettlab.com (opens in a new tab) |
Running AI on the Zettlab D4
It can, with limits: expect small models only, at modest speed. Models run on its CPU cores, and this configuration leaves about 12.0 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 |
|---|---|
| AnythingLLM | From the NAS app store |
| Any Docker image | In a container (Docker) |
| Ollama / Open WebUI or other model runners as Docker containers | In a container (Docker) |
AI features from Zettlab
| Feature | What it does | Where the AI runs |
|---|---|---|
| ZettAI AI Search | Natural-language search across images, audio, video and documents stored on the NAS; maker says processing is 100% on-device. | On the NAS |
| ZettAI AI Categories | Automatic sorting and tagging of files and media. | On the NAS |
| ZettAI AI Transcription / AI Clip | Audio and video transcription and clip finding. | On the NAS |
| ZettAI AI Q&A (via PC Computing Power) | Cloud service or another computer |
Best LLMs for the Zettlab D4
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 78Great quality (A) · 78 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | Gemma 4 12B | Q4_K_M | 9.5 GB | 3.0 tok/s | Slow |
| 77Great quality (A) · 77 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. | K2 Horizon 7B | Q5_K_M | 9.2 GB | 3.3 tok/s | Slow |
| 66Good quality (B) · 66 of 100: how capable the model is at Q4_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Mellum2.1 Thinking (12B-A2.5B) | Q4_K_M | 9.1 GB | 13.8 tok/s | Runs well |
| 75Great quality (A) · 75 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. | MiMo V2.6 Distill Qwen 9B | Q5_K_M | 8.5 GB | 3.2 tok/s | Slow |
| 75Great quality (A) · 75 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. | SenseNova Loop 9B Preview | Q5_K_M | 8.9 GB | 3.1 tok/s | Slow |
| 58Good quality (B) · 58 of 100: how capable the model is at Q3_K_M, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | Maple Preview (20B-A1B) | Q3_K_M | 11.6 GB | 28.6 tok/s | Runs welltight fit |
| 74Great quality (A) · 74 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.5 9B | Q5_K_M | 8.7 GB | 3.1 tok/s | Slow |
| 73Great quality (A) · 73 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3.5 9B | Q5_K_M | 8.7 GB | 3.1 tok/s | Slow |
| 72Great quality (A) · 72 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | Ornith 1.0 9B | Q5_K_M | 8.7 GB | 3.1 tok/s | Slow |
| 71Great quality (A) · 71 of 100: how capable the model is at Q5_K_M, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. | TMax 9B | Q5_K_M | 8.2 GB | 3.4 tok/s | Slow |
Best Image models for the Zettlab D4
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 84Great quality (A) · 84 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. | FLUX 3 Image Klein | Q4 GGUF | 10.2 GB | 21.8 min | Very slow |
| 76Great quality (A) · 76 of 100: how capable the model is at FP8, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. | FLUX.2 [klein] 4B | FP8 | 10.2 GB | 2.9 min | Very slow |
| 78Great quality (A) · 78 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 77/100 (quality, fit, speed and memory use) sets the ranking. | Z-Image Turbo | Q4 GGUF | 10.1 GB | 9.6 min | Very slow |
| 79Great quality (A) · 79 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE-Image Turbo | Q4 GGUF | 11.3 GB | 12.3 min | Very slowtight fit |
| 76Great quality (A) · 76 of 100: how capable the model is at Q4 GGUF, whatever it runs on. Match score 75/100 (quality, fit, speed and memory use) sets the ranking. | Z-Image | Q4 GGUF | 10.1 GB | 65.1 min | Very slow |
| 87Excellent quality (A+) · 87 of 100: how capable the model is at Q8 GGUF, whatever it runs on. Match score 72/100 (quality, fit, speed and memory use) sets the ranking. | ERNIE-Image | Q8 GGUF | 11.2 GB | 84.8 min | Very slowtight fit · encoder unloaded after use |
Best Video models for the Zettlab D4
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 49Fair quality (C) · 49 of 100: how capable the model is at FP8, whatever it runs on. Match score 63/100 (quality, fit, speed and memory use) sets the ranking. | LTX-Video 2B | FP8 | 10.8 GB | 71.8 min | Very slowtight fit |
| 83Great quality (A) · 83 of 100: how capable the model is at FP8, whatever it runs on. Match score 62/100 (quality, fit, speed and memory use) sets the ranking. | Bernini-R A14B (video generation + editing) | FP8 | 10.7 GB | 44.8 h | Very slowtight fit · CPU offload |
| 74Great quality (A) · 74 of 100: how capable the model is at FP8, whatever it runs on. Match score 61/100 (quality, fit, speed and memory use) sets the ranking. | HY-OmniWeaving (8.3B, unified video) | FP8 | 7.8 GB | 33.0 h | Very slowCPU offload |
| 55Good quality (B) · 55 of 100: how capable the model is at FP16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.1 T2V 1.3B | FP16 | 8.4 GB | 13.4 h | Very slowencoder unloaded after use |
| 55Good quality (B) · 55 of 100: how capable the model is at FP16, whatever it runs on. Match score 60/100 (quality, fit, speed and memory use) sets the ranking. | Wan 2.1 VACE 1.3B | FP16 | 10.1 GB | 14.5 h | Very slowencoder unloaded after use |
Best Decision models for the Zettlab D4
| Quality | Model | Quant | Memory | Speed | Runs |
|---|---|---|---|---|---|
| 78Great quality (A) · 78 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. | OpenAI Privacy Filter | Q8_0 | 2.4 GB | 162 ms | Runs well |
| 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 | 6.1 GB | 23.6 s | Very slow |
| 86Excellent quality (A+) · 86 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. | Jina Reranker v3.5 | Q8_0 | 2.4 GB | 3.5 s | Very slow |
| 89Excellent quality (A+) · 89 of 100: how capable the model is at Q6_K, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. | Qwen3 Reranker 8B | Q6_K | 8.6 GB | 47.9 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 | 6.1 GB | 23.6 s | Very slow |
| 84Great quality (A) · 84 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 | Q8_0 | 2.4 GB | 3.5 s | Very slow |
| 90Excellent quality (A+) · 90 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. | Skywork Reward V2 Llama 3.1 8B | Q8_0 | 10.4 GB | 94.7 s | Very slowtight fit |
| 80Great quality (A) · 80 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. | GLiNER2.5 Decide | Q8_0 | 1.2 GB | 1.5 s | Very slow |
Other products with the Rockchip RK3588 NAS (16 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.