96GB max RAM · 5 bays · 10GbE
AINAS Score 79
£1,040.41
Amazon UK · Verified
Can the NIMO Nexus Pro run local AI?
Yes, the NIMO Nexus Pro can run local language models. It pairs AMD Ryzen 7 PRO 8845HS and a 16 TOPS NPU with up to 96GB of memory, which suits 70B class models at 4-bit with room left for longer context (Estimated).
It also has a GPU path (Full-size GPU), so a graphics card can be added later for much faster inference.
Local LLM support is documented by the manufacturer.
The NIMO Nexus Pro is a four-bay tower that treats a full-size graphics card as part of the design rather than an afterthought. It has a PCIe 4.0 x16 slot wired at x8 that takes cards up to 330mm long, an 800W power supply with a 400W budget for the GPU, and NIMO sells it bundled with RTX 50-series cards.
The base platform is a Ryzen 7 PRO 8845HS with eight cores, Radeon 780M graphics and a 16 TOPS NPU, with DDR5 memory up to 96GB. Two 10GbE ports, three M.2 slots and one USB4 port complete it. NIMO says a fitted GPU lets it run models up to 70B locally, and community reports confirm Ollama and Open WebUI working.
That makes it one of the few systems where you can buy a GPU-equipped AI NAS as one product. The trade-offs are a young brand, a US-focused store and a ZimaOS-based operating system that is less mature than QNAP or Synology. Check UK availability and support before you buy.
Not currently on Amazon UK
We could not find a UK listing for the NIMO Nexus 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 | NIMO brand store listing and product gallery claim up to 70B LLMs locally with a full-size GPU installed |
| Ollama | Yes | Community confirmed | Community solution shows Ollama container running on ZimaOS (generic ZimaOS, not this unit) |
| Open WebUI | Yes | Community confirmed | Community solution shows Open WebUI with Ollama on ZimaOS |
| RAG | Limited | Vendor confirmed | Marketing claims folders become a natural language searchable knowledge base; no technical detail |
| AI search | Yes | Vendor confirmed | Natural language search across photos, videos and documents |
| GPU expansion | Yes | Vendor confirmed | PCIe 4.0 x16 (x8) full-size GPU slot, 400W budget; RTX 5060/5070/5080 bundles sold |
| Hardware acceleration | Limited | Unverified | Radeon 780M iGPU and media server use shown; hardware transcoding not explicitly stated |
| AI photos | Yes | Vendor confirmed | Gallery shows semantic photo search |
| AI video | No | Unverified | Not mentioned |
| Surveillance AI | Limited | Vendor confirmed | Gallery image advertises NVR mode; no NVR software details |
The Nexus Pro ships with 8GB of DDR5 5600 SO-DIMM and supports up to 96GB with ECC. Upgrading to the maximum lifts the model ceiling from small models up to around 7B parameters to 70B class models at 4-bit with room left for longer context (both Estimated).
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, 96GB leaves space for a model of roughly 146B parameters at most (Estimated).
ECC memory support is a plus for always-on systems that also hold important files.
Yes. The Nexus Pro has a 1x PCIe 4.0 x16 (x8 electrical), GPU up to 330mm x 66mm, 400W GPU power budget 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 800W power supply first.
The 16 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.
With limits. The Nexus Pro can host a small RAG stack such as AnythingLLM or Open WebUI with a compact embedding model, but memory and compute restrict how large the answering model can be. It suits a personal document library more than a team knowledge base.
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 |
|---|---|---|---|
| 8GB RAM + 128GB SSD, no GPU | 8GB | 128GB | Base configuration without a graphics card |
| 32GB RAM + 128GB SSD + RTX 5060 | 32GB | 128GB | Bundled with an NVIDIA RTX 5060 |
| 32GB RAM + 128GB SSD + RTX 5070 | 32GB | 128GB | Bundled with an NVIDIA RTX 5070 |
| 32GB RAM + 128GB SSD + RTX 5080 | 32GB | 128GB | Bundled with an NVIDIA RTX 5080 |
The Nexus Pro scores best for Local LLM (83/100) and RAG (79/100). It suits people who want a private chat assistant or coding model at home without sending data to a cloud service.
Other Native AI NAS systems closest in overall score.
Yes. Ollama support is confirmed by community reports. See the capability table above for the source.
Yes. Open WebUI support is confirmed by community reports. 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.
Partly. Surveillance AI support is documented by the manufacturer. See the capability table above for the source.
Partly. Hardware acceleration support is not yet verified. See the capability table above for the source.
It has 2 x 10GbE built in, and the 1x PCIe 4.0 x16 (x8 electrical), GPU up to 330mm x 66mm, 400W GPU power budget 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.