96GB max RAM · 4 bays · 2 x 10GbE
AINAS Score 81
No verified UK price
View
Can the UGREEN iDX6011 run local AI?
It can. The UGREEN iDX6011 combines Intel Core Ultra 5 125H and a 11 TOPS NPU with as much as 64GB of memory, enough for 32B class models comfortably, and 70B class models at 4-bit with little headroom (Estimated).
Its PCIe x8 slot leaves room to add a GPU when you outgrow CPU inference.
Local LLM support is documented by the manufacturer.
The iDX6011 is the more affordable way into UGREEN's AI-first NAS line, and it keeps most of what makes the Pro interesting. It runs a Core Ultra 5 125H with 14 cores, Intel Arc graphics and an 11 TOPS NPU, and it gets the same iDX-only software: the Uliya local assistant, semantic file search and Intelligent Learning.
Memory is soldered, so choose carefully at checkout. UGREEN sells it with 32GB or 64GB of LPDDR5X and neither can be upgraded later. The 32GB version handles 7B to 14B class models; the 64GB version is the one to buy if you want 32B class models or plan to run an assistant alongside other containers.
It shares the internal PCIe Gen4 x8 slot, two 10GbE ports, six drive bays and two M.2 slots with the Pro. What it drops is OCuLink, the front display and the faster CPU. For buyers who want local AI on a UGREEN, the 64GB iDX6011 covers 32B class models at a lower price than the Pro. Only buy the Pro if you specifically need OCuLink for an external GPU dock.
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 local AI assistant supported on iDX series; local LLM via Model Manager. |
| Ollama | Yes | Vendor confirmed | UGREEN KB documents Ollama plus Open WebUI via Docker Compose on UGOS Pro. |
| Open WebUI | Yes | Vendor confirmed | Official UGOS Pro Docker Compose guide. |
| RAG | Yes | Vendor confirmed | Uliya knowledge base Q&A; RAG model via Model Manager. |
| AI search | Yes | Vendor confirmed | Universal Search AI semantic search and Intelligent Learning on iDX. |
| GPU expansion | Yes | Vendor confirmed | Internal PCIe 4.0 x8 slot and Thunderbolt 4 eGPU; no OCuLink on this model. |
| Hardware acceleration | Yes | Vendor confirmed | 11 TOPS NPU plus Arc iGPU (18 TOPS). |
| AI photos | Yes | Vendor confirmed | AI Album with smart recognition and OCR search. |
| AI video | Yes | Vendor confirmed | Photos face detection in photos and videos; voice transcription in Voice Memos. |
| Surveillance AI | Yes | Vendor confirmed | Surveillance Center with local AI detection on iDX. |
32GB of LPDDR5X is all the iDX6011 will ever have; it is not user-upgradeable. Every model you run has to fit inside that figure alongside the operating system.
Our estimate for the biggest model that fits in 64GB is about 93B parameters at 4-bit, after setting aside 8GB for the system. Long context windows reduce that figure (Estimated).
Yes, through a 1x PCIe Gen4 x8 (internal). That is the single biggest upgrade for local AI on the iDX6011: model layers move into fast graphics memory and replies speed up dramatically. Card size and power are the constraints.
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 iDX6011 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.
For network access it has 2 x 10GbE. Fast enough that the network will not be the bottleneck.
| Configuration | RAM | SSD | Notes |
|---|---|---|---|
| 32GB | 32GB | None | Diskless; soldered LPDDR5X |
| 64GB | 64GB | None | Diskless; soldered LPDDR5X |
The closest UGREEN model by AINAS Score. Only the specifications that differ are listed.
Best fit: home lab owners who want one box for storage, containers, media and a few AI services. That is where the iDX6011 scores highest (Home Lab 72/100), followed by Local LLM (71/100).
Other Native AI NAS systems closest in price.
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.