96GB max RAM · 5 bays · 10GbE
AINAS Score 62
No verified UK price
View
Can the UGREEN DXP480T Plus run local AI?
Only lightly. Expect 32B class models comfortably, and 70B class models at 4-bit with little headroom (Estimated) on the UGREEN DXP480T Plus: Intel Core i5-1235U does the work with up to 64GB of memory, which is fine for experiments rather than a daily assistant.
Without any GPU option, the processor carries the whole inference load.
Local LLM support is documented by the manufacturer.
The DXP480T Plus is a compact all-flash NAS with four M.2 slots and no hard drive bays. It shares the Core i5-1235U with the larger DXP models and supports up to 64GB of DDR5, which is unusual headroom for something this small.
For AI it sits at the edge of the AI Ready class. There is no NPU and no internal slot for a graphics card, so inference runs on the CPU, and UGREEN's Uliya assistant is limited to iDX models. What it does have is a 10GbE port and two Thunderbolt 4 ports. UGREEN's documentation says NVIDIA GPUs work over Thunderbolt, so an external enclosure is possible, but that is a workaround rather than a design feature.
It suits creators and developers who want fast flash storage on the desk, with enough memory to host a small private assistant or an embedding model for search. If you need capacity rather than speed, a bay-based model makes more sense, because four M.2 drives get expensive quickly.
Amazon UK
8GB
£773.99£859.99
Verified
In stock
View dealProduct 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 | Limited | Vendor confirmed | CPU-only Ollama in Docker; no NPU; Uliya iDX only. |
| Ollama | Yes | Vendor confirmed | UGREEN KB Docker Compose guide on UGOS Pro. |
| Open WebUI | Yes | Vendor confirmed | Official UGOS Pro guide. |
| RAG | Limited | Vendor confirmed | RAG via Open WebUI only. |
| AI search | Limited | Vendor confirmed | Photos description search; document semantic search is iDX only. |
| GPU expansion | Limited | Vendor confirmed | Thunderbolt 4 eGPU dock only; no PCIe slot. |
| Hardware acceleration | Limited | Vendor confirmed | Quick Sync on Iris Xe; no NPU. |
| AI photos | Yes | Vendor confirmed | AI Photo Album. |
| AI video | Limited | Vendor confirmed | Photos AI via Model Manager on DXP. |
| Surveillance AI | Yes | Vendor confirmed | Surveillance Center supports DXP series. |
Plan on upgrading. 8GB is fitted as standard, while the DXP480T Plus accepts 64GB of DDR5 SODIMM, which is the difference between small models up to around 7B parameters and 32B class models comfortably, and 70B class models at 4-bit with little headroom (Estimated).
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).
A graphics card is not an option on the DXP480T Plus, which has neither a PCIe slot nor OCuLink. Inference runs on the CPU, with Intel Iris Xe Graphics handling media tasks, so keep to small models.
As the storage half of a RAG setup it works well; as the model host it is limited. Small embedding models run fine on the DXP480T Plus, while the answering model needs more compute than it has.
For network access it has 10GbE. Fast enough that the network will not be the bottleneck.
| Configuration | RAM | SSD | Notes |
|---|---|---|---|
| 8GB | 8GB | None | Diskless, 8GB DDR5, 128GB system SSD. UK bundles: + UPS, + M.2 SSD enclosure. |
The closest UGREEN model by AINAS Score. Only the specifications that differ are listed.
Best fit: small offices that need shared storage with private AI tools and room to grow. That is where the DXP480T Plus scores highest (Business 49/100), followed by Local LLM (48/100).
Less suited to buyers who expect to add a graphics card later.
Other AI Ready 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.
Partly. Hardware acceleration support is documented by the manufacturer. See the capability table above for the source.
It has 10GbE built in. The fastest port is 10GbE.
Every field records its source. Specifications were last checked on . Spot an error? Send a correction with a manufacturer link.