96GB max RAM · 5 bays · 10GbE
AINAS Score 79
£1,040.41
Amazon UK · Verified

Can the Zettlab D6 Ultra run local AI?
Yes. Intel Core Ultra 5 125H and a 11 TOPS NPU, backed by a 96GB memory ceiling, lets the Zettlab D6 Ultra handle 70B class models at 4-bit with room left for longer context (Estimated).
A graphics card can be added through its PCIe x8 slot, which is the biggest single speed upgrade for local models.
Local LLM support is documented by the manufacturer.
The Zettlab D6 Ultra is a six-bay NAS designed around local AI from the start, and the hardware backs that up. It uses Intel's Core Ultra 5 125H with Arc graphics and an NPU, 32GB of DDR5 that expands to 96GB, two 10GbE ports, two USB4 ports and an external PCIe 4.0 x8 connector for a graphics card.
ZettOS ships with a local assistant that can download models such as Gemma, Phi, QwQ, DeepSeek R1 and Llama, plus natural language search across documents, images and audio. Reviews from TechRadar and XDA confirm those features working on real units.
The problem is availability. As of October 2026 Zettlab lists the Ultra models as sold-out pre-orders with no confirmed shipping date, and its shipping policy does not include the UK. We list it as announced and keep the page because the specifications are firm. If it reaches UK buyers it would be a direct rival to the UGREEN iDX6011, with the advantage of upgradeable memory.
Not currently on Amazon UK
We could not find a UK listing for the Zettlab D6 Ultra 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.
Each capability shows how it was confirmed: Verified by AINAS, Vendor confirmed, Community confirmed or Unverified.
| Capability | Supported | Evidence | Note |
|---|---|---|---|
| Local LLM | Yes | Vendor confirmed | Spec table lists Local LLM and AI; TechRadar saw downloadable Gemma, Phi, QwQ, DeepSeek-R1 and Llama models; XDA says default chat model likely Qwen3-4B |
| Ollama | Limited | Unverified | No Ollama app or ZettOS guide found; Docker with Compose is supported so it is plausible via container |
| Open WebUI | Limited | Unverified | No Open WebUI app or guide found; plausible via Docker |
| RAG | Yes | Vendor confirmed | ZettAI learns NAS documents, images, audio and video for AI Q&A and chat over your files |
| AI search | Yes | Vendor confirmed | Natural language search over image content, voice content, documents, names |
| GPU expansion | Limited | Unverified | SFF-8654 PCIe 4.0 x8 external connector; wiki says external GPUs not recommended without official confirmation; no tested eGPU found |
| 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 video | Yes | Vendor confirmed | Video and audio files are learned for content search; AI Transcription listed |
| Surveillance AI | Yes | Vendor confirmed | Surveillance Management app for ONVIF/RTSP IP cameras |
Out of the box the D6 Ultra has 32GB; the official ceiling is 96GB of DDR5 5600 SO-DIMM (dual channel). A memory upgrade is the cheapest way to make it more useful for AI.
Working backwards from 96GB: reserve about 8GB for the operating system and storage services, and at roughly 0.6GB per billion parameters at 4-bit, the largest model that fits is around 146B (Estimated).
It can. A 1x external SFF-8654 connector (PCIe 4.0 x8); no internal PCIe card slot listed is the route, and a card with 16GB or more of its own memory changes what the D6 Ultra can run. Measure the space and check the 240W power budget before ordering.
Its 11 TOPS NPU is used by the vendor's own AI features. Open-source LLM runtimes generally ignore NAS NPUs today, so it adds little to chat model speed.
It is a good fit. RAG needs two models in memory at once, one to index and one to answer, plus fast access to the documents, and the D6 Ultra has both the memory and 6 bays + 2 x M.2. Support is documented by the manufacturer.
The manufacturer also provides AI search across your files (documented by the manufacturer), which covers simple document questions without setting up your own stack.
Built-in networking: 2 x 10GbE. Plenty for a shared knowledge base with several users.
| Configuration | RAM | SSD | Notes |
|---|---|---|---|
| Without RAM | None | 256GB | Barebone, no memory; 256GB system SSD; pre-order only when checked |
| 32GB | 32GB | 256GB | 32GB DDR5 fitted; 256GB system SSD; pre-order only when checked |
The closest Zettlab model by AINAS Score. Only the specifications that differ are listed.
Its strongest AINAS profiles are Local LLM at 78 and RAG at 77, which points to people who want a private chat assistant or coding model at home without sending data to a cloud service.
Look elsewhere if you are anyone who needs a system they can buy and receive today.
Other Native AI NAS systems closest in overall score.
Partly. Ollama support is not yet verified. See the capability table above for the source.
Partly. Open WebUI support is not yet verified. See the capability table above for the source.
Yes. AI photos support is documented by the manufacturer. See the capability table above for the source.
Yes. Surveillance AI support is documented by the manufacturer. See the capability table above for the source.
Yes. Hardware acceleration support is documented by the manufacturer. See the capability table above for the source.
It has 2 x 10GbE built in, and the 1x external SFF-8654 connector (PCIe 4.0 x8); no internal PCIe card slot listed can take a faster network card. The fastest port is 2 x 10GbE.
Every field records its source. Specifications were last checked on . Spot an error? Send a correction with a manufacturer link.