64GB max RAM · 4 bays · 10GbE
AINAS Score 43
No verified UK price
View
Can the ASUSTOR Lockerstor 4 Gen3 (AS6804T) run local AI?
Partly. The ASUSTOR Lockerstor 4 Gen3 (AS6804T) runs local models on AMD Ryzen Embedded V3C14 alone, and its 64GB ceiling allows 32B class models comfortably, and 70B class models at 4-bit with little headroom (Estimated), but replies will be slow without graphics acceleration.
No graphics card can be fitted, which keeps every model on the CPU.
Local LLM support is documented by the manufacturer.
The Lockerstor 4 Gen3 is the four-bay version of ASUSTOR's current platform: Ryzen Embedded V3C14, ECC DDR5 up to 64GB, four M.2 slots, two 10GbE and two 5GbE ports and two USB4 ports. For a four-bay NAS that is an unusually fast network and storage setup.
The AI picture matches the rest of the AS68 range. App Central officially lists Ollama with Open WebUI, so you can run small models on the four CPU cores, and Photo Gallery recognises faces locally. There is no integrated graphics, no NPU and no GPU path, so local language models will be slow and limited in size.
At its UK launch price it competes with the UGREEN DXP4800 Plus and the Synology DS925+. It beats both on networking and ECC memory, and matches the UGREEN on memory ceiling, but none of the three is a real AI machine. Choose it for fast, reliable storage with official app support for light AI tools.
Amazon UK
16GB
£1,239
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 | ASUSTOR App Central lists Ollama + Open WebUI for AS68 series (ADM 5.0+). CPU-only inference on a 4-core V3C14 with no GPU; ASUSTOR's RAG page recommends an external GPU host for inference. An ASUSTOR-hosted media review video shows llama.cpp + OpenClaw on the AS6804T (no figures in page text). |
| Ollama | Yes | Vendor confirmed | Ollama + Open WebUI app (v0.11.4.r01) lists AS68 series as supported; installs via Docker. |
| Open WebUI | Yes | Vendor confirmed | Bundled with the Ollama + Open WebUI App Central package. |
| RAG | Limited | Vendor confirmed | ASUSTOR markets NAS as RAG knowledge base storage with vector DBs (Chroma, pgvector, Weaviate) via Docker; Open WebUI app includes RAG. Inference recommended on external compute. |
| AI search | No | Unverified | No AI or semantic search feature found in ADM 5.1 material. |
| GPU expansion | No | Vendor confirmed | No PCIe expansion slot listed on spec page; no integrated GPU. ASUSTOR states its NAS models do not feature a discrete GPU. |
| Hardware acceleration | No | Community confirmed | Ryzen Embedded V3C14 has no integrated graphics (NASCompares, CNX Software); spec page lists multimedia output N/A. No NPU. |
| AI photos | Yes | Vendor confirmed | Photo Gallery 4.2 (ADM 5.1.1+) supports AS68 series; ADM 5.1 adds facial recognition grouping powered by locally run AI. |
| AI video | No | Unverified | No AI video feature found in ADM documentation. |
| Surveillance AI | Yes | Vendor confirmed | Surveillance Center 2.8.4 and Surveillance Center 3 list AS68 series as supported. |
Out of the box the Lockerstor 4 Gen3 (AS6804T) has 16GB; the official ceiling is 64GB of DDR5-4800 ECC SO-DIMM with ECC support. A memory upgrade is the cheapest way to make it more useful for AI.
Working backwards from 64GB: reserve about 8GB for the operating system and storage services, and at roughly 0.6GB per billion parameters at 4-bit, the largest model that fits is around 93B (Estimated).
ECC support protects against silent memory errors on a box that runs around the clock.
There is no supported way to add a GPU to the Lockerstor 4 Gen3 (AS6804T): no PCIe slot and no OCuLink. Inference runs on the CPU, so keep to small models.
For a personal library, yes. A compact embedding model and a small chat model will run, but the Lockerstor 4 Gen3 (AS6804T) is better as the document store behind a RAG system whose model runs on stronger hardware.
Built-in networking: 2 x 10GbE + 2 x 5GbE. Plenty for a shared knowledge base with several users.
| Configuration | RAM | SSD | Notes |
|---|---|---|---|
| 16GB | 16GB | None | Diskless; 1x 16GB ECC DDR5-4800 pre-installed, 2 SO-DIMM slots |
The closest ASUSTOR model by AINAS Score. Only the specifications that differ are listed.
Its strongest AINAS profiles are Home Lab at 49 and Business at 47, which points to home lab owners who want one box for storage, containers, media and a few AI services.
Look elsewhere if you are buyers who expect to add a graphics card later.
Other AI Capable 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.
No. Hardware acceleration support is confirmed by community reports. See the capability table above for the source.
It has 2 x 10GbE + 2 x 5GbE built in. 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.