2GB max RAM · 2 bays · 1GbE
AINAS Score 16
£169.15£238
Amazon UK · Verified

Traditional NASStationPC
Why Traditional NAS: ARM Rockchip RK3568B2 (4x Cortex-A55) with a 1 TOPS NPU, Mali-G52 iGPU, no GPU path and 4GB LPDDR4 only; AI is limited to photo recognition and search.
Updated
Can the StationPC PA100 Pro run local AI?
No. The StationPC PA100 Pro is a storage-first Traditional NAS: Rockchip RK3568B2 and at most 4GB of memory leave no room for a local language model.
It is here as a reference point against systems that can run AI.
The PA100 Pro is a small, low-power StationOS box for someone who wants photo organisation and photo search at home, not local AI models. It has a Rockchip RK3568B2 with 4 cores, a 1 TOPS NPU and one M.2 NVMe slot, and it takes a 30W USB-C input. StationOS adds AI photo organisation with face and scene recognition, and Smart Search lets you find photo content with text. Both are vendor confirmed. It supports Docker through custom container images and Compose files, and it carries a 2-year warranty. It scores 16 on the AINAS Score, which reflects how little AI headroom it has. Treat it as a compact photo and file box, with 4GB of LPDDR4 memory that sets the limit on everything else.
The 4GB of LPDDR4 memory rules the PA100 Pro out for anyone who wants to run language models. It is the maximum, and it cannot be expanded. StationPC staff say local NPU AI is only on the roadmap, and the vendor confirms local LLM is not supported. There is also no GPU path: no PCIe, OCuLink or USB4. Every model listed on this page is marked as not fitting (Estimated), starting with Llama 3.2 3B. Buyers who want private chat, document search or creative AI should look for a system with much more memory, ideally expandable, plus a PCIe slot, OCuLink or USB4 for a graphics card, and a supported local model runtime. It also has no wired network port on the unit itself: Wi-Fi 6 is built in, and 2.5GbE comes only with the optional Dock.
No verified price
We have not verified a listing for the StationPC PA100 Pro at a retailer we track. The specifications below stand on their own; a price appears here as soon as a 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 or Amazon.com, as applicable, 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 | No | Vendor confirmed | 4GB RAM ARM; StationPC staff say local NPU AI is only on the roadmap |
| Ollama | No | Unverified | No Ollama support; user request only |
| Open WebUI | No | Unverified | No source; 4GB RAM |
| RAG | No | Unverified | Not offered |
| AI search | Yes | Vendor confirmed | Text-based search of photo content (Smart Search) |
| GPU expansion | No | Vendor confirmed | No PCIe, OCuLink or USB4 |
| Hardware acceleration | Limited | Vendor confirmed | Media Center 4K decoding; transcoding not mentioned |
| AI photos | Yes | Vendor confirmed | AI photo organisation with face and scene recognition |
| AI video | No | Unverified | Not mentioned |
| Surveillance AI | No | Unverified | Not mentioned on StationOS page |
Calculated from the PA100 Pro's memory and each model's published size at each quantization. Rows marked Estimated are calculations, not benchmarks. Check any model.
| Model | Best quantization | Runs? | Memory needed | Expected performance | Verification |
|---|---|---|---|---|---|
| Llama 3.2 3BLlama, 3.21B | None fits | No | 11GB at Q4 | Not measured | Estimated |
| Llama 3.1 8BLlama, 8.03B | None fits | No | 14GB at Q4 | Not measured | Estimated |
| Qwen3 8BQwen, 8.19B | None fits | No | 15GB at Q4 | Not measured | Estimated |
| Gemma 3 12BGemma, 11.8B | None fits | No | 18GB at Q4 | Not measured | Estimated |
| Qwen3 14BQwen, 14.8B | None fits | No | 20GB at Q4 | Not measured | Estimated |
| Phi-4 14BPhi, 14.7B | None fits | No | 19GB at Q4 | Not measured | Estimated |
| Mistral Small 3 24BMistral, 23.6B | None fits | No | 25GB at Q4 | Not measured | Estimated |
| Gemma 3 27BGemma, 27B | None fits | No | 29GB at Q4 | Not measured | Estimated |
| Qwen3 30B A3BQwen, 30.5B | None fits | No | 31GB at Q4 | Not measured | Estimated |
| Qwen3 32BQwen, 32.8B | None fits | No | 32GB at Q4 | Not measured | Estimated |
| DeepSeek-R1 32B (Qwen distill)DeepSeek, 32.8B | None fits | No | 32GB at Q4 | Not measured | Estimated |
| Llama 3.3 70BLlama, 70.6B | None fits | No | 60GB at Q4 | Not measured | Estimated |
| Llama 4 Scout 17Bx16ELlama, 109B | None fits | No | 89GB at Q4 | Not measured | Estimated |
| Qwen2.5 72BQwen, 72.7B | None fits | No | 65GB at Q4 | Not measured | Estimated |
| Mistral Large 2 123BMistral, 123B | None fits | No | 96GB at Q4 | Not measured | Estimated |
One verdict per workload, from the PA100 Pro's use-case scores and capability rows. Unknown means we cannot confirm it, not that it probably works.
The verdict for local LLM work is poor. The vendor confirms local LLM is not supported, 4GB of RAM on an ARM chip is the ceiling, and StationPC staff say local NPU AI is only on the roadmap.
Private RAG is poor on the PA100 Pro. RAG is listed as not offered, Open WebUI and Ollama are both unsupported, and all three rows are unverified rather than confirmed, with only 4GB of RAM to work with.
AI search is rated poor overall, even though one form exists. Smart Search offers text-based search of photo content and is vendor confirmed, but it covers photos only and the system has just 4GB of RAM and a 1 TOPS NPU.
AI photos is rated poor, despite the feature being vendor confirmed. StationOS offers AI photo organisation with face and scene recognition, but the 1 TOPS NPU and 4GB of RAM limit how far it goes in practice.
Surveillance is a poor fit for the PA100 Pro. The surveillance capability is listed as no and is unconfirmed, because the StationOS page does not mention it, and storage is limited to one M.2 NVMe slot with no drive bays.
Home lab use is rated poor overall. Docker is supported through custom container images and Compose files, but virtual machine support is not confirmed, there are no drive bays, and the memory is a fixed 4GB.
Business use is rated poor for the PA100 Pro. The unit has no drive bays, one M.2 NVMe slot, fixed 4GB memory, no listed ECC support, and Wi-Fi 6 only, with 2.5GbE needing the optional Dock.
Creative AI work is rated poor on the PA100 Pro. There is no GPU expansion (vendor confirmed: no PCIe, OCuLink or USB4), hardware acceleration is limited to Media Center 4K decoding with transcoding not mentioned, and local LLM is not supported.
Memory on the PA100 Pro is fixed at 4GB of LPDDR4. There are no slots to add more, so choose the largest configuration you can justify on day one.
There is no supported way to add a GPU to the PA100 Pro: no PCIe slot and no OCuLink. Inference runs on the CPU, with Arm Mali-G52-2EE handling media tasks, so keep to small models.
Its 1 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.
Not well. A useful private RAG setup needs more memory or compute than the PA100 Pro offers.
The manufacturer also provides AI search across your files (documented by the manufacturer), which covers simple document questions without setting up your own stack.
Built-in networking: Not stated. Adequate for a household, slower for bulk indexing.
| Configuration | RAM | SSD | Notes |
|---|---|---|---|
| PA100 Pro | 4GB | None | Diskless, SKU SPC00-PRO-US / SPC00-PRO-EU. |
| PA100 Pro & Dock | 4GB | None | With Dock (adds 2.5GbE and second M.2), SKU SPC00-PRO-US-SPC01. |
| PA100 Pro 2TB | 4GB | 2TB | 2TB SSD pre-installed, SKU SPC00-PRO-US-2TB. |
| PA100 Pro & Dock 2TB each | 4GB | 4TB | 2TB pre-installed in unit and Dock, SKU SPC00-PRO-US-SPC01-2TB. |
Its strongest AINAS profiles are Local LLM at 16 and RAG at 15, which points to people who want a private chat assistant or coding model at home without sending data to a cloud service.
Look elsewhere if you are anyone who wants to run models larger than about 8B parameters, or buyers who expect to add a graphics card later.
Other Traditional NAS systems closest in overall score.
No. Llama 3.2 3B is the first model listed on this page and it is marked as not fitting at Q4 or Q8 (Estimated). The vendor also confirms local LLM is not supported, and StationPC staff say local NPU AI is only on the roadmap. The system has 4GB of LPDDR4 memory and a 1 TOPS NPU, but nothing on it is confirmed to run local models. Buyers who want local chat should look for a system with a supported model runtime.
No. The 4GB of LPDDR4 memory is the maximum, and the PA100 Pro is not expandable. Both the included and maximum memory are 4GB. The source for the maximum notes no upgrade path, although confidence in that is medium. If you need more memory for any workload, look for a system with expandable memory and a higher maximum. ECC support is not stated for this system either.
Yes, one. The PA100 Pro has 1 M.2 NVMe 2280 slot and no SATA drive bays, so all internal storage goes there. The vendor lists up to 8TB in its FAQ, and the PCIe generation is not published. The optional Dock adds a second M.2 slot. The 2TB configuration comes with a 2TB SSD pre-installed, and the diskless version has no SSD. Internal storage is the only expansion inside the unit.
No. The unit has no PCIe slot, OCuLink port or USB4 port, and GPU expansion is vendor confirmed as not supported. Its graphics come from an integrated Arm Mali-G52-2EE. There are 0 Thunderbolt ports. The USB ports are one USB-A (USB3.0) and a Type-C port. Anyone planning to add a graphics card later should look for a system with a PCIe slot, OCuLink or USB4.
Four configurations are listed: the PA100 Pro diskless, the PA100 Pro 2TB, the PA100 Pro & Dock, and the PA100 Pro & Dock 2TB each. All have 4GB of memory. The unit alone has Wi-Fi 6 only. The Dock adds 2.5GbE and a second M.2 slot. The Dock 2TB bundle has 2TB pre-installed in the unit and in the Dock. Every version uses the same Rockchip RK3568B2 and 1 TOPS NPU.
Yes. StationOS supports custom container images and Compose files, according to the manufacturer page, though that source does not name models and confidence is medium. Virtual machine support is not confirmed. The operating system is StationOS, with no version given. Docker support does not make local LLM work possible, as the vendor confirms local LLM is not supported on the PA100 Pro with 4GB of RAM.
No. Ollama support is not yet verified. See the capability table above for the source.
No. Open WebUI support is not yet verified. 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.
No. Surveillance AI support is not yet verified. 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 Not stated built in. The fastest port is Not stated.
Every field records its source. Specifications were last checked on . Spot an error? Send a correction with a manufacturer link.