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

Can the UGREEN iDX6011 Pro run local AI?
Yes, the UGREEN iDX6011 Pro can run local language models. It pairs Intel Core Ultra 7 255H and a 13 TOPS NPU with up to 64GB of memory, which suits 32B class models comfortably, and 70B class models at 4-bit with little headroom (Estimated).
It also has a GPU path (PCIe x8 slot), so a graphics card can be added later for much faster inference.
Local LLM support is documented by the manufacturer.
The iDX6011 Pro is UGREEN's most capable NAS for local AI and one of the few systems we track built around a laptop-class AI processor. The Core Ultra 7 255H gives it 16 cores, Arc 140T graphics and a 13 TOPS NPU, and UGREEN's own local assistant, Uliya, runs on it through the Model Manager. That assistant only runs on the iDX series, so this is the UGREEN to buy if you want local AI without building your own stack.
The catch is memory. All 64GB is soldered LPDDR5X, so there is no upgrade path and no way to reach the 96GB or 128GB that larger models want. In practice that means 32B class models are comfortable and 70B class models are a squeeze.
What sets the Pro apart from the standard iDX6011 is the fixed 64GB, the faster CPU, a front touch display and an OCuLink port alongside the internal PCIe Gen4 x8 slot. With two 10GbE ports and six bays it also works as a full storage server. It is priced at the very top of the consumer NAS market, so weigh it against the iDX6011 64GB, which shares most of the hardware.
Not currently on Amazon UK
We could not find a UK listing for the UGREEN iDX6011 Pro 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 | Uliya AI assistant runs local models via Model Manager; iDX series only. ComputerBase names local Qwen3. |
| Ollama | Yes | Vendor confirmed | UGREEN KB documents Ollama plus Open WebUI via Docker Compose on UGOS Pro; Marius Hosting guide tested on iDX6011 Pro. |
| Open WebUI | Yes | Vendor confirmed | Official UGOS Pro Docker Compose guide for Open WebUI (ollama image). |
| RAG | Yes | Vendor confirmed | Uliya knowledge base Q&A over uploaded documents; Model Manager downloads RAG model. |
| AI search | Yes | Vendor confirmed | Universal Search AI semantic search and Intelligent Learning (iDX only). ComputerBase found file content search not working in its test. |
| GPU expansion | Yes | Vendor confirmed | OCuLink (PCIe 4.0 x4), internal PCIe 4.0 x8 and Thunderbolt 4 eGPU paths; NVIDIA driver and Docker toolkit in App Center. |
| Hardware acceleration | Yes | Vendor confirmed | 13 TOPS NPU and Arc 140T (74 TOPS); Uliya settings include GPU acceleration. |
| AI photos | Yes | Vendor confirmed | AI Album with face, object, scene and text recognition. |
| AI video | Yes | Vendor confirmed | Photos detects faces in photos and videos; Universal Search covers videos. |
| Surveillance AI | Yes | Vendor confirmed | Surveillance Center with local AI detection (people, vehicle, package, pet). |
The iDX6011 Pro ships with 64GB of LPDDR5X 8400 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, 64GB leaves space for a model of roughly 93B parameters at most (Estimated).
Yes. The iDX6011 Pro has a 1x PCIe Gen4 x8 (internal) that can take a graphics card. A discrete GPU with its own memory runs models far faster than CPU inference and lets the NAS serve several users at once. Check card length, height and power draw against the chassis and the 300W power supply first.
It also has an OCuLink port, a second route to an external GPU dock.
The 13 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.
Yes. Retrieval augmented generation keeps your documents on the NAS and feeds the relevant passages to a local model. The iDX6011 Pro has the memory for an embedding model alongside a chat model, and 6 bays + 2 x M.2 for the library. 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.
Networking is 2 x 10GbE. That is ample for indexing large libraries and for several people querying at once.
| Configuration | RAM | SSD | Notes |
|---|---|---|---|
| 64GB | 64GB | None | Only configuration sold; diskless with a 128GB system SSD |
The closest UGREEN model by AINAS Score. Only the specifications that differ are listed.
The iDX6011 Pro scores best for Home Lab (73/100) and Business (73/100). It suits home lab owners who want one box for storage, containers, media and a few AI services.
Other Native AI NAS systems closest in overall score.
Yes. Ollama support is documented by the manufacturer. See the capability table above for the source.
Yes. Open WebUI support is documented by the manufacturer. 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 PCIe Gen4 x8 (internal) 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.