16GB max RAM · 6 bays · 2.5GbE
AINAS Score 41
No verified UK price
View
Can the StationPC DA400 run local AI?
Yes, the StationPC DA400 can run local language models. It pairs Rockchip RK3588 and a 6 TOPS NPU with up to 8GB of memory, which suits small models up to around 7B parameters (Estimated).
There is no way to add a discrete GPU, so all inference runs on the CPU and basic integrated graphics.
Local LLM support is documented by the manufacturer.
What is the DA400 like?
The StationPC DA400 is a crowdfunded four-bay NAS with an unusual approach to local AI: alongside its Rockchip RK3588 processor it carries a separate RK1828 AI module with its own 5GB of memory, which StationPC says runs language models up to 8B parameters at up to 50 tokens per second. That claim is from the manufacturer and has not been independently tested.
The rest of the hardware is modest. The NAS has 8GB of fixed LPDDR4, two 2.5GbE ports, one M.2 slot and no PCIe or GPU expansion, so there is no growth path beyond the small models the module handles. StationOS Pro is Debian-based and supports Docker, and the AI features cover semantic search, photo recognition and document questions.
Its Kickstarter campaign closed in October 2026 and it is not yet on general sale, so we list it as announced. It is worth watching if you want a low-power box with a ready-made private assistant, but wait for shipping units and reviews before relying on it.
Current UK offers
Not currently on Amazon UK
We could not find a UK listing for the StationPC DA400 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
- Not stated
- Released
- 2026
Can the DA400 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 | Yes | Vendor confirmed | Runs local LLMs up to 8B (Qwen, Gemma) on RK1828 module, up to 50 tokens/s claimed |
| Ollama | Limited | Unverified | Docker supported on ARM StationOS Pro; no Ollama source found |
| Open WebUI | Limited | Unverified | Docker supported; no source found |
| RAG | Yes | Vendor confirmed | AI chat over local files, document summary, knowledge-base Q&A |
| AI search | Yes | Vendor confirmed | Semantic and natural language file and photo search, OCR |
| GPU expansion | No | Vendor confirmed | No PCIe slot, OCuLink or USB4 |
| Hardware acceleration | Limited | Vendor confirmed | StationOS Pro page claims real-time transcoding; RK3588 has hardware video decode/encode |
| AI photos | Yes | Vendor confirmed | AI photo library, people/pet/scene categorisation, similar photo detection |
| AI video | No | Unverified | Not mentioned |
| Surveillance AI | No | Unverified | Not mentioned |
How much RAM does the DA400 support?
The DA400 ships with 8GB of LPDDR4 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.
Can you add a GPU to the DA400?
No. The DA400 has no PCIe slot or OCuLink port for a graphics card. Inference runs on the CPU, with Arm Mali-G610 MC4 handling media tasks, 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 DA400 suitable for RAG?
Yes. Retrieval augmented generation keeps your documents on the NAS and feeds the relevant passages to a local model. The DA400 has the memory for an embedding model alongside a chat model, and 4 bays + 1 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 2.5GbE. Fine for one or two users; indexing a large archive over the network will be slower.
Which DA400 configurations are sold?
| Configuration | RAM | SSD | Notes |
|---|---|---|---|
| 8GB LPDDR4 + 64GB eMMC | 8GB | None | Single configuration; 64GB eMMC system drive; diskless |
Who should buy the DA400?
The DA400 scores best for Home Lab (41/100) and Business (41/100). 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 DA400?
Other Native AI NAS systems closest in overall score.
DA400 questions
Can the DA400 run Ollama?
Partly. Ollama support is not yet verified. See the capability table above for the source.
Does Open WebUI work on the DA400?
Partly. Open WebUI support is not yet verified. See the capability table above for the source.
Does the DA400 do AI photo recognition?
Yes. AI photos support is documented by the manufacturer. See the capability table above for the source.
Can the DA400 run AI surveillance?
No. Surveillance AI support is not yet verified. See the capability table above for the source.
Does the DA400 have hardware AI acceleration?
Partly. Hardware acceleration support is documented by the manufacturer. See the capability table above for the source.
How fast is the DA400's network?
It has 2 x 2.5GbE built in. The fastest port is 2 x 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.