64GB max RAM · 6 bays · 2 x 10GbE
AINAS Score 74
£1,999.99
Amazon UK · Verified
Can the Zettlab D6 run local AI?
The Zettlab D6 can run small local models, with limits. Its Rockchip RK3588 and 16GB memory ceiling suit 7B to 8B class models (Estimated), so treat it as a storage-first NAS that can host light AI tools.
There is no way to add a discrete GPU, so all inference runs on the CPU.
Local LLM support is documented by the manufacturer.
What is the D6 like?
The Zettlab D6 is the original, non-Ultra six-bay model, and it takes a very different approach to AI from the Ultra versions. It runs on a Rockchip RK3588 with a 6 TOPS NPU and 16GB of fixed memory, which is enough for Zettlab's on-device photo recognition, transcription and semantic search, but not for running a language model on the NAS itself.
Zettlab is clear about this: the D6's AI question-answering runs through a companion app using your computer's processing power. We still class it as a Native AI NAS because AI search and media understanding are the core of the product, but it sits right at the boundary with AI Capable.
Networking is 1GbE plus 2.5GbE, there is one M.2 slot, and there is no GPU path. The D6 is on sale through Zettlab's own store, which ships to the US, Australia and Singapore but not the UK. If you want local language models running on the NAS, the D6 Ultra is the model to wait for.
Current UK offers
Not currently on Amazon UK
We could not find a UK listing for the Zettlab D6 from a retailer we track. The specifications below stand on their own; a price appears here as soon as a UK listing is confirmed.
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon.co.uk at the time of purchase will apply to the purchase of this product.
Key specifications
- Docker
- Yes
- VM support
- Yes
- Released
- 2025
Can the D6 run local LLMs?
Each capability shows how it was confirmed: Verified by AINAS, Vendor confirmed, Community confirmed or Unverified.
| Capability | Supported | Evidence | Note |
|---|---|---|---|
| Local LLM | Limited | Vendor confirmed | AI Q&A listed as via PC Computing Power: the LLM runs on a companion Windows/Mac app, not on the NAS; Local LLM is listed only for Ultra models |
| Ollama | Limited | Unverified | No Ollama app or guide found; ARM64 Docker is supported but RK3588 with 16GB fixed RAM limits model size |
| Open WebUI | Limited | Unverified | No Open WebUI app or guide found; plausible via Docker |
| RAG | Limited | Vendor confirmed | Document Q&A over NAS files offered, but generation relies on PC computing power |
| AI search | Yes | Vendor confirmed | Natural language search across images, audio, video and documents |
| GPU expansion | No | Vendor confirmed | No PCIe expansion, no OCuLink, no USB4 |
| Hardware acceleration | Yes | Vendor confirmed | H.264 and H.265 8/10-bit codecs listed; ZettOS states hardware encoding and decoding |
| AI photos | Yes | Vendor confirmed | Photos app with People and Pets, scene grouping, duplicate detection; AI Categories |
| AI video | Yes | Vendor confirmed | AI Transcription and video content search listed |
| Surveillance AI | Yes | Vendor confirmed | Surveillance Management app for ONVIF/RTSP IP cameras |
How much RAM does the D6 support?
The D6 ships with 16GB of LPDDR4x that cannot be upgraded, so the configuration you buy is the one you keep. For local AI that matters more than anything else on the spec sheet: model size is capped by memory, not storage.
As a rule of thumb, a 4-bit model needs about 0.6GB per billion parameters plus room for context. After leaving around 8GB for the NAS operating system, 16GB leaves space for a model of roughly 13B parameters at most (Estimated).
Can you add a GPU to the D6?
No. The D6 has no PCIe slot or OCuLink port for a graphics card. Inference runs on the CPU, so keep to small models.
The 6 TOPS NPU helps with photo recognition, transcription and vendor AI features. Most open-source runtimes such as Ollama do not use NAS NPUs yet, so do not count it towards language model speed.
Is the D6 suitable for RAG?
With limits. The D6 can host a small RAG stack such as AnythingLLM or Open WebUI with a compact embedding model, but memory and compute restrict how large the answering model can be. It suits a personal document library more than a team knowledge base.
The manufacturer also provides AI search across your files (documented by the manufacturer), which covers simple document questions without setting up your own stack.
Networking is 2.5GbE + 1GbE. Fine for one or two users; indexing a large archive over the network will be slower.
Which D6 configurations are sold?
| Configuration | RAM | SSD | Notes |
|---|---|---|---|
| 16GB | 16GB | None | Single configuration; 16GB LPDDR4x soldered; 32GB eMMC system storage; diskless |
How is the D6 different from the D6 Ultra?
The closest Zettlab model by AINAS Score. Only the specifications that differ are listed.
- Processor: Rockchip RK3588 on the D6, Intel Core Ultra 5 125H on the D6 Ultra
- CPU cores: 8 on the D6, 14 on the D6 Ultra
- NPU: 6 TOPS on the D6, 11 TOPS on the D6 Ultra
- Integrated graphics: none on the D6, Intel Arc on the D6 Ultra
- Memory fitted: 16GB on the D6, 32GB on the D6 Ultra
- Memory ceiling: 16GB on the D6, 96GB on the D6 Ultra
- M.2 slots: 1 on the D6, 2 on the D6 Ultra
- Networking: 2.5GbE + 1GbE on the D6, 2 x 10GbE on the D6 Ultra
- GPU path: None on the D6, PCIe x8 slot on the D6 Ultra
- Power supply: none on the D6, 240W on the D6 Ultra
- Status: tracked on the D6, announced on the D6 Ultra
- AINAS Score: 41 on the D6, 78 on the D6 Ultra
Who should buy the D6?
The D6 scores best for Home Lab (39/100) and Business (39/100). It suits home lab owners who want one box for storage, containers, media and a few AI services.
It is a weaker fit for anyone who wants to run models larger than about 8B parameters and for buyers who expect to add a graphics card later.
What are the alternatives to the D6?
Other Native AI NAS systems closest in overall score.
D6 questions
Can the D6 run Ollama?
Partly. Ollama support is not yet verified. See the capability table above for the source.
Does Open WebUI work on the D6?
Partly. Open WebUI support is not yet verified. See the capability table above for the source.
Does the D6 do AI photo recognition?
Yes. AI photos support is documented by the manufacturer. See the capability table above for the source.
Can the D6 run AI surveillance?
Yes. Surveillance AI support is documented by the manufacturer. See the capability table above for the source.
Does the D6 have hardware AI acceleration?
Yes. Hardware acceleration support is documented by the manufacturer. See the capability table above for the source.
How fast is the D6's network?
It has 2.5GbE + 1GbE built in. The fastest port is 2.5GbE.
Where do these specifications come from?
Every field records its source. Specifications were last checked on . Spot an error? Send a correction with a manufacturer link.
- zettlab.com: USB4 listed as -
- zettlab.com: Power adapter included but wattage not published
- nascompares.com: Max RAM equals included 16GB on spec page; NASCompares says soldered, not upgradable
- wangdoo.com: Base D4 and D6 shipped in late 2025, about six months late; store listing created Nov 2025
- zettlab.com: D6 variant available (Add to cart) on manufacturer store
- zettlab.com: ZettOS says running VMs on standard D4 and D6 may impact performance; NASCompares prototype review (Apr 2025) listed VMs as coming soon
- zettlab.com