AINAS
TerraMaster T6-423 6-bay NAS

TerraMaster T6-423

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 short answer

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.

Current offers

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.

Key specifications

CPU
Intel Celeron N5095
Source: Manufacturer
GPU
Intel UHD Graphics
Source: Official docs
Included RAM
4GB DDR4 non-ECC SODIMM
Source: Manufacturer
Maximum RAM
32GB
Source: Manufacturer
Networking
2 x 2.5GbE
Source: Manufacturer
GPU expansion
None
Source: Manufacturer
Power supply
120W
Source: Manufacturer
Docker
Yes
VM support
Yes
Released
2022
Segment
Desktop

Can the T6-423 run local LLMs?

Each capability shows how it was confirmed: Verified by AINAS, Vendor confirmed, Community confirmed or Unverified.

CapabilitySupportedEvidenceNote
Local LLMLimitedUnverifiedLow-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.
OllamaLimitedVendor confirmedRuns 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 YesVendor confirmedOpen WebUI container via Docker; same TerraMaster blog source.
RAGLimitedUnverifiedPossible through Open WebUI or similar containers; no TerraMaster or community source showing RAG on TOS.
AI searchLimitedVendor confirmedTOS 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 NoVendor confirmedSpec lists no PCIe slot; no USB4, Thunderbolt or OCuLink.
Hardware acceleration YesVendor confirmedHardware transcoding engine H.264/H.265/MPEG-4/VC-1 up to 4K60 via Intel iGPU. Video only, no NPU.
AI photos YesVendor confirmedTOS 7 Photos: AI face recognition and AI scene recognition (80+ categories).
AI video NoUnverifiedNo AI video feature found in TOS 7 material.
Surveillance AI YesVendor confirmedTOS 7 Surveillance Manager supports up to 32 ONVIF IP cameras.

What AI models can the T6-423 run?

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.

ModelBest quantizationRuns?Memory neededExpected performanceVerification
Llama 3.2 3BLlama, 3.21BQ8Yes13GBNot measuredEstimated
Llama 3.1 8BLlama, 8.03BQ8Yes19GBNot measuredEstimated
Qwen3 8BQwen, 8.19BQ8Yes19GBNot measuredEstimated
Gemma 3 12BGemma, 11.8BQ8Yes24GBNot measuredEstimated
Qwen3 14BQwen, 14.8BQ8Yes28GBNot measuredEstimated
Phi-4 14BPhi, 14.7BQ8Yes28GBNot measuredEstimated
Mistral Small 3 24BMistral, 23.6BQ4Yes25GBNot measuredEstimated
Gemma 3 27BGemma, 27BQ4Yes29GBNot measuredEstimated
Qwen3 30B A3BQwen, 30.5BQ4Yes31GBNot measuredEstimated
Qwen3 32BQwen, 32.8BQ4Yes32GBNot measuredEstimated
DeepSeek-R1 32B (Qwen distill)DeepSeek, 32.8BQ4Yes32GBNot measuredEstimated
Llama 3.3 70BLlama, 70.6BNone fitsNo60GB at Q4Not measuredEstimated
Llama 4 Scout 17Bx16ELlama, 109BNone fitsNo89GB at Q4Not measuredEstimated
Qwen2.5 72BQwen, 72.7BNone fitsNo65GB at Q4Not measuredEstimated
Mistral Large 2 123BMistral, 123BNone fitsNo96GB at Q4Not measuredEstimated

Workload fit

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.

Local LLMPoor fit

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 RAGPoor fit

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 searchPoor fit

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 photosOK

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.

SurveillanceOK

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 labOK

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.

BusinessOK

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 AIPoor fit

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.

How much RAM does the T6-423 support?

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).

Can you add a GPU to the T6-423?

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.

Is the T6-423 suitable for RAG?

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.

Limitations

  • No GPU path. The T6-423 has no PCIe slot, USB4, Thunderbolt or OCuLink, so a graphics card or external GPU cannot be added for AI work.
  • No NPU, and the CPU is a 4-core Intel Celeron N5095 with integrated UHD Graphics. Its hardware acceleration is video transcoding only.
  • Memory starts at 4GB and is non-ECC DDR4 SODIMM. It can be expanded to 32GB, but there is no ECC option.
  • Local LLM and RAG support are both unverified, and the vendor's Ollama and Open WebUI guidance covers x86 TOS NAS generally, not this model.
  • Networking stops at 2 x 2.5GbE. With no PCIe slot there is no way to add a 10GbE card, so large file transfers across six bays share those two ports.

Which T6-423 configurations are sold?

ConfigurationRAMSSDNotes
4GB4GBNoneOnly configuration; 1x 4GB DDR4, 2 slots (32GB max).

How is the T6-423 different from the F6-424 Max?

The closest TerraMaster model by bay count and AINAS Score. Only the specifications that differ are listed.

  • Processor: Intel Celeron N5095 on the T6-423, Intel Core i5-1235U on the F6-424 Max
  • CPU cores: 4 on the T6-423, 10 on the F6-424 Max
  • Integrated graphics: Intel UHD Graphics on the T6-423, Intel Iris Xe Graphics on the F6-424 Max
  • Memory fitted: 4GB on the T6-423, 8GB on the F6-424 Max
  • Memory ceiling: 32GB on the T6-423, 64GB on the F6-424 Max
  • Networking: 2 x 2.5GbE on the T6-423, 2 x 10GbE on the F6-424 Max
  • Power supply: 120W on the T6-423, 150W on the F6-424 Max
  • AI class: AI Capable on the T6-423, AI Ready on the F6-424 Max
  • AINAS Score: 37 on the T6-423, 52 on the F6-424 Max

See the full TerraMaster F6-424 Max page

Who should buy the T6-423?

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.

What are the alternatives to the T6-423?

Other AI Capable systems closest in overall score.

Lincplus LincStation N2

Lincplus LincStation N2

Lincplus

AI Capable

16GB max RAM · 2 bays · 10GbE

AINAS Score 38

$409.99

Amazon US · Verified

Ships from the US; delivery and import charges shown at checkout

View

Common questions

Can the T6-423 run DeepSeek-R1 32B?

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.

Can you upgrade the memory in the T6-423?

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.

Can the T6-423 take a graphics card?

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.

Does the T6-423 have M.2 slots?

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).

Can the T6-423 run virtual machines?

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.

Does the T6-423 run Docker?

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.

Does Ollama work on the T6-423?

Partly. Ollama support is documented by the manufacturer. See the capability table above for the source.

Can you install Open WebUI on the T6-423?

Yes. Open WebUI support is documented by the manufacturer. See the capability table above for the source.

Can the T6-423 sort photos by faces and objects?

Yes. AI photos support is documented by the manufacturer. See the capability table above for the source.

Is the T6-423 good for AI camera recording?

Yes. Surveillance AI support is documented by the manufacturer. See the capability table above for the source.

Is there hardware acceleration for AI on the T6-423?

Yes. Hardware acceleration support is documented by the manufacturer. See the capability table above for the source.

What networking does the T6-423 have?

It has 2 x 2.5GbE built in. The fastest port is 2 x 2.5GbE.

Where do these specifications come from?

Every field records its source. Specifications were last checked on . Spot an error? Send a correction with a manufacturer link.