16GB max RAM · 12 x M.2 · 10GbE
AINAS Score 36
£634.99
Amazon UK · Verified

AI CapableTerraMaster
Why AI Capable: Intel Celeron N5095 (4 cores, UHD Graphics, no NPU), 4GB shipped and 32GB max DDR4, no PCIe or other GPU path: Docker-capable x86 but only tiny models.
Updated
Can the TerraMaster T6-423 run local AI?
Partly. The TerraMaster T6-423 runs local models on Intel Celeron N5095 alone, and its 32GB ceiling allows models up to the 14B class, with 32B class models a tight fit (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 not yet verified.
The T6-423 suits a buyer who wants a six-bay home or small-office NAS with light container use. It has 6 bays, 2 M.2 slots and 2 x 2.5GbE, plus TOS 7 with Docker and virtual machines. Memory is a Intel Celeron N5095 platform with DDR4 non-ECC SODIMM, 4GB shipped and 32GB maximum, so it can be expanded. TOS 7 Photos covers AI face and scene recognition, and Surveillance Manager handles up to 32 ONVIF IP cameras (both vendor confirmed). The AINAS Score is 37, which reflects a storage-first machine, not an AI one.
The main constraint is the lack of any GPU path. The T6-423 has no PCIe slot, no USB4, no Thunderbolt and no OCuLink, and no NPU. Anyone who wants to run larger local models at usable quality, or do creative AI work, should look for a system with a PCIe slot or a fast external GPU connection, an NPU or a discrete GPU, and a higher memory ceiling. Memory capacity alone does not fix this, because the CPU and integrated Intel UHD Graphics are the only compute available. Local LLM support here is unverified.
No verified price
We have not verified a listing for the TerraMaster T6-423 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 | Limited | Unverified | Low-power CPU with small shipped RAM and no GPU path; only very small models via Docker would be practical. TerraMaster blog describes Ollama/Open WebUI via Docker on x86 TOS NAS generally, not this model. |
| Ollama | Limited | Vendor confirmed | Runs as a Docker container via TOS Docker Manager per TerraMaster blog (x86 TOS NAS generally). Practical only for tiny models on this hardware. |
| Open WebUI | Yes | Vendor confirmed | Open WebUI container via Docker; same TerraMaster blog source. |
| RAG | Limited | Unverified | Possible through Open WebUI or similar containers; no TerraMaster or community source showing RAG on TOS. |
| AI search | Limited | Vendor confirmed | TOS 7 OpenClaw agent and AI tagging allow natural-language queries; setup uses an API key from a provider such as OpenAI, so cloud LLM. Global search is an inverted index, not semantic. |
| GPU expansion | No | Vendor confirmed | Spec lists no PCIe slot; no USB4, Thunderbolt or OCuLink. |
| Hardware acceleration | Yes | Vendor confirmed | Hardware transcoding engine H.264/H.265/MPEG-4/VC-1 up to 4K60 via Intel iGPU. Video only, no NPU. |
| AI photos | Yes | Vendor confirmed | TOS 7 Photos: AI face recognition and AI scene recognition (80+ categories). |
| AI video | No | Unverified | No AI video feature found in TOS 7 material. |
| Surveillance AI | Yes | Vendor confirmed | TOS 7 Surveillance Manager supports up to 32 ONVIF IP cameras. |
Calculated from the T6-423'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 | Q8 | Yes | 13GB | Not measured | Estimated |
| Llama 3.1 8BLlama, 8.03B | Q8 | Yes | 19GB | Not measured | Estimated |
| Qwen3 8BQwen, 8.19B | Q8 | Yes | 19GB | Not measured | Estimated |
| Gemma 3 12BGemma, 11.8B | Q8 | Yes | 24GB | Not measured | Estimated |
| Qwen3 14BQwen, 14.8B | Q8 | Yes | 28GB | Not measured | Estimated |
| Phi-4 14BPhi, 14.7B | Q8 | Yes | 28GB | Not measured | Estimated |
| Mistral Small 3 24BMistral, 23.6B | Q4 | Yes | 25GB | Not measured | Estimated |
| Gemma 3 27BGemma, 27B | Q4 | Yes | 29GB | Not measured | Estimated |
| Qwen3 30B A3BQwen, 30.5B | Q4 | Yes | 31GB | Not measured | Estimated |
| Qwen3 32BQwen, 32.8B | Q4 | Yes | 32GB | Not measured | Estimated |
| DeepSeek-R1 32B (Qwen distill)DeepSeek, 32.8B | Q4 | Yes | 32GB | 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 T6-423's use-case scores and capability rows. Unknown means we cannot confirm it, not that it probably works.
The T6-423 is a poor choice for local LLMs. Local LLM support is limited and unverified, there is no GPU path or NPU, and only very small models via Docker would be practical on the Celeron.
Private RAG is a poor fit on the T6-423. RAG is limited and unverified, with no TerraMaster or community source showing it on TOS, though Open WebUI as a Docker container is vendor confirmed.
AI search is a poor fit here. TOS 7 natural-language queries need an API key from a cloud provider, and the built-in global search is an inverted index, not semantic (vendor confirmed, limited).
AI photos are an acceptable fit for the T6-423. TOS 7 Photos offers AI face recognition and AI scene recognition across 80+ categories, vendor confirmed.
Surveillance is an acceptable fit. TOS 7 Surveillance Manager supports up to 32 ONVIF IP cameras (vendor confirmed), and the Intel iGPU handles video transcoding up to 4K60.
Home lab use is acceptable on the T6-423. Docker and virtual machines are both supported, and memory expands from 4GB shipped to 32GB, with two 2.5GbE ports.
Business use is acceptable for file storage and light services. It has 6 bays, 2 M.2 slots, 2 x 2.5GbE and a 2 year warranty, but no ECC memory.
Creative AI is a poor fit. GPU expansion is not supported (vendor confirmed), and the iGPU's hardware acceleration covers video transcoding only, with no NPU.
Out of the box the T6-423 has 4GB; the official ceiling is 32GB of DDR4 non-ECC SODIMM. A memory upgrade is the cheapest way to make it more useful for AI.
Working backwards from 32GB: 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 40B (Estimated).
There is no supported way to add a GPU to the T6-423: no PCIe slot and no OCuLink. Inference runs on the CPU, with Intel UHD Graphics handling media tasks, so keep to small models.
For a personal library, yes. A compact embedding model and a small chat model will run, but the T6-423 is better as the document store behind a RAG system whose model runs on stronger hardware.
Built-in networking: 2 x 2.5GbE. Adequate for a household, slower for bulk indexing.
| Configuration | RAM | SSD | Notes |
|---|---|---|---|
| 4GB | 4GB | None | Only configuration; 1x 4GB DDR4, 2 slots (32GB max). |
The closest TerraMaster model by bay count and AINAS Score. Only the specifications that differ are listed.
Its strongest AINAS profiles are Home Lab at 41 and Business at 40, 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, or teams moving large files over the network every day.
Other AI Capable systems closest in overall score.
Yes on paper, at Q4 only. Estimated: DeepSeek-R1 32B (Qwen distill) needs 20GB at Q4 and fits within the 32GB maximum. Estimated: it does not fit at Q8, which needs 35GB. This is a memory calculation, not a benchmark. Local LLM support on the T6-423 is limited and unverified, and there is no GPU path, so only very small models are practical.
Yes. The T6-423 ships with 4GB (1x 4GB DDR4) and has 2 SODIMM slots, with a maximum of 32GB. The memory type is DDR4 non-ECC SODIMM, so ECC modules are not supported. The memory sits in slots rather than being soldered.
No. The T6-423 has no PCIe slot, and no USB4, Thunderbolt or OCuLink port, so there is no route to add a graphics card or external GPU (vendor confirmed). Its Intel UHD Graphics handles video transcoding only, and there is no NPU.
Yes, 2. The T6-423 has 2 M.2 NVMe slots alongside its 6 drive bays. TerraMaster's TOS 7 notice lists this model as conditionally compatible, with a BIOS boot order change needed if TOS is installed on NVMe (community-sourced, low confidence).
Yes. TOS 7 supports virtual machines on the T6-423 as well as Docker. The 4-core Intel Celeron N5095 and the 4GB fitted make that a light job, since TOS, containers and a guest system all share the same memory. Adding a second module toward the 32GB maximum across the 2 slots is the first step for anyone planning a virtual machine alongside storage and Surveillance Manager, and TerraMaster rates Ollama here as practical only for tiny models.
Yes. Docker is listed on the TerraMaster product page, and TOS 7 also supports virtual machines (KVM). Open WebUI as a Docker container is vendor confirmed. Ollama is limited and practical only for tiny models on this hardware.
Partly. 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.
Yes. Hardware acceleration support is documented by the manufacturer. 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.