16GB max RAM · 2 bays · 2.5GbE
AINAS Score 30
£279.99
Amazon UK · Verified

AI CapableCWWK
Why AI Capable: Intel N150 (or i3-N355) with no NPU, Intel UHD iGPU only, no PCIe or OCuLink GPU path and a 32GB largest DDR5 option, so small Docker models at best.
Updated
Can the CWWK X86-P6 Pocket NAS run local AI?
The CWWK X86-P6 Pocket NAS can run small local models, with limits. Its Intel N150 and nullGB memory ceiling suit only very small models of around 1B to 3B parameters (Estimated), so treat it as a storage-first NAS that can host light AI tools.
There is no way to add a discrete GPU, so all inference runs on the CPU.
Local LLM support is not yet verified.
The X86-P6 Pocket NAS suits buyers who want a small, all-flash storage box they set up themselves, and it scores 20 on the AINAS Score, so AI is a side note here. It has four M.2 NVMe slots, two 2.5GbE ports and an Intel N150 CPU. There are no drive bays, so storage is M.2 only. Memory is DDR5 4800 and the board is listed as expandable, with 32GB as the largest factory option. The power supply is rated at 60W. The operating system is not stated, so you install your own. Docker and virtual machine support are not stated either. Buy it if you want compact flash storage on a network and are happy to configure the software yourself. It is sold barebone with no memory or storage, or with 8GB, 16GB or 32GB of DDR5 already fitted.
The limit that rules it out for many buyers is local AI. It has no GPU path, with no PCIe slot, OCuLink or USB4, and the vendor confirms GPU expansion is not supported. Every model listed on this page, from Llama 3.2 3B up, is marked as not fitting at Q4 or Q8 (Estimated). Local LLM and Ollama support are limited and unconfirmed. Ollama and Open WebUI depend on an operating system you install yourself. Anyone who wants to run language models at home should look for a system with a PCIe slot, OCuLink or USB4 for a graphics card, an NPU, and a memory ceiling above 32GB. Check that the vendor confirms container support. This box suits file storage and network duties, not model work.
Amazon UK
N150, barebone (no RAM, no storage)
£281.31
Verified
In stock
Buy on AmazonAmazon UK
N150, 16GB DDR5, 256GB NVMe
£645.77
Verified
In stock
Buy on AmazonProduct 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 | Limited | Unverified | N150 CPU-only, up to 32GB factory option; no evidence. |
| Ollama | Limited | Unverified | Depends on user-installed OS; no evidence. |
| Open WebUI | Limited | Unverified | Depends on user-installed OS; no evidence. |
| RAG | Limited | Unverified | No evidence. |
| AI search | No | Unverified | No NAS software bundled. |
| GPU expansion | No | Vendor confirmed | No PCIe slot, OCuLink or USB4. |
| Hardware acceleration | Limited | Unverified | Intel N-series iGPU (Quick Sync) presumed but not named on the CWWK page. |
| AI photos | Limited | Unverified | Self-hosted only; no evidence. |
| AI video | No | Unverified | Not listed. |
| Surveillance AI | Limited | Unverified | Self-hosted only; no evidence. |
Calculated from the X86-P6 Pocket NAS'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 X86-P6 Pocket NAS's use-case scores and capability rows. Unknown means we cannot confirm it, not that it probably works.
We cannot confirm local LLM use on the X86-P6 Pocket NAS. Local LLM support is limited and Unverified, the notes say CPU-only on the N150 with up to 32GB as a factory option, and every model listed on this page is an Estimated no fit.
Private RAG is unconfirmed here, so we cannot call it a match. The RAG capability is limited and Unverified with no evidence, and Open WebUI and Ollama both depend on an operating system you install yourself, with none stated.
AI search is a poor fit on the X86-P6 Pocket NAS. AINAS lists it as no, because no NAS software is bundled, and that entry is Unverified, so any search tool would be something you add and test yourself.
We cannot confirm AI photo features on the X86-P6 Pocket NAS. Support is limited and Unverified, the notes say it is self-hosted only with no evidence, and no NPU is listed, so it would depend on the CPU alone.
We cannot confirm surveillance use on the X86-P6 Pocket NAS. Support is limited and Unverified, self-hosted only with no evidence, and there are no drive bays, so storage is limited to the four M.2 slots.
We cannot confirm home lab suitability for the X86-P6 Pocket NAS. It has four M.2 slots and two 2.5GbE ports, but the operating system, Docker support and virtual machine support are all unstated for this system.
Business use is a poor fit for the X86-P6 Pocket NAS. It has no ECC memory, no drive bays and no stated warranty term, and no operating system or Docker support is stated by the vendor.
We cannot confirm creative AI on the X86-P6 Pocket NAS. GPU expansion is not supported (vendor confirmed), hardware acceleration is limited and Unverified, and local LLM support is also limited and Unverified, with the iGPU presumed but not named by the vendor.
The X86-P6 Pocket NAS supports up to an unstated amount ofGB of DDR5 4800.
No. The X86-P6 Pocket NAS has no PCIe slot or OCuLink port for a graphics card. Inference runs on the CPU, so keep to small models.
With limits. The X86-P6 Pocket NAS 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.
Networking is 2 x 2.5GbE. Fine for one or two users; indexing a large archive over the network will be slower.
| Configuration | RAM | SSD | Notes |
|---|---|---|---|
| N150, barebone (no RAM, no storage) | None | None | |
| i3-N355, barebone | None | None | |
| N150, 8GB DDR5, 128GB NVMe | 8GB | 128GB | |
| N150, 16GB DDR5, 256GB NVMe | 16GB | 256GB | |
| N150, 32GB DDR5, 1TB NVMe | 32GB | 1TB |
The X86-P6 Pocket NAS scores best for Business (23/100) and Home Lab (22/100). It suits small offices that need shared storage with private AI tools and room to grow.
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.
Other AI Capable systems closest in price.
Buying guides that list it
No. Llama 3.2 3B needs 2GB at Q4 and 3.4GB at Q8, and it is marked as not fitting at either level (Estimated). That is a calculation, not a benchmark. Every larger model listed on this page is also an Estimated no fit. Local LLM support on the X86-P6 Pocket NAS is limited and Unverified, and the notes describe it as N150 CPU-only with no evidence.
Yes, the memory is listed as expandable. It is DDR5 4800, and the barebone version comes with no memory fitted. The largest factory option is 32GB, and the maximum the board accepts is not published. CWWK does not confirm other limits, so check with CWWK before fitting a larger module. Factory configurations come with 8GB, 16GB or 32GB of DDR5.
No. The vendor confirms GPU expansion is not supported, with no PCIe slot, OCuLink or USB4 listed. The system has two USB 3.2 ports only. It has no Thunderbolt ports and no USB4 ports. The only graphics hardware is the Intel iGPU, which is presumed but not named on the vendor page, and hardware acceleration is limited and Unverified, so there is no external GPU route.
Five are listed. Four use the Intel N150: a barebone with no memory or storage, 8GB of DDR5 with a 128GB NVMe drive, 16GB with 256GB, and 32GB with a 1TB NVMe drive. The fifth is an i3-N355 barebone. Every version has the same four M.2 NVMe slots, two 2.5GbE ports and a 60W power supply, and none states an operating system, so you install your own. The 32GB version is the largest factory memory option, and CWWK does not publish a maximum.
Yes, four. The vendor image shows a PCIe 3.0 x4 M.2 connection on the core board split into four M.2 NVMe 2280 slots at x1 each, through an adapter board. There are no drive bays, so M.2 is the only storage. That suits all-flash use. Plan around x1 links per drive when thinking about throughput. Fitted versions include 128GB, 256GB or 1TB of NVMe.
No, Docker is not confirmed for the X86-P6 Pocket NAS, and neither is the operating system, because it is sold as a Pocket NAS or board PC with no OS listed. Ollama and Open WebUI are limited and Unverified, and both depend on the operating system you install. Virtual machine support is not stated either. You would need to confirm container support yourself.
Partly. Ollama support is not yet verified. See the capability table above for the source.
Partly. Open WebUI support is not yet verified. See the capability table above for the source.
Partly. AI photos support is not yet verified. See the capability table above for the source.
Partly. Surveillance AI support is not yet verified. 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 2.5GbE built in. The fastest port is 2 x 2.5GbE.
Every field records its source. Specifications were last checked on . Spot an error? Send a correction with a manufacturer link.