64GB max RAM · 4 bays · 2 x 10GbE
AINAS Score 45
No verified UK price
View
Can the QNAP TVS-h674T run local AI?
Only lightly. Expect 32B class models comfortably, and 70B class models at 4-bit with little headroom (Estimated) on the QNAP TVS-h674T: Intel Core i5-12400 does the work with up to 64GB of memory, which is fine for experiments rather than a daily assistant.
Its PCIe x16 slot leaves room to add a GPU when you outgrow CPU inference.
Local LLM support is documented by the manufacturer.
The TVS-h674T is the six-bay sibling of the TVS-h874T, with a Core i5-12400, 32GB of memory expandable to 64GB, and the same Thunderbolt 4 card fitted. We class it as AI Capable rather than AI Ready because QNAP's official GPU list caps it at a 4GB card and the power supply is 250W, so meaningful GPU inference is not realistic.
What it can do is run small to mid-sized models on the CPU through Ollama in Container Station, host Qsirch semantic search, and handle face and object recognition in QuMagie quickly thanks to the Intel graphics. It also supports Hailo-8 accelerator cards for vision tasks such as surveillance.
Buy it for a small studio or office that wants Thunderbolt editing storage and QNAP's mature app ecosystem, with AI as a supporting feature. If you want a NAS that runs a useful chat assistant on its own, look at systems with a modern AI processor or a full-size GPU slot instead.
Amazon UK
TVS-h674T-i5-32G
£3,161
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 | QNAP Ollama guide applies (x86, 16GB+ for 7B); supported GPUs are 4GB or less so inference is CPU-bound. |
| Ollama | Yes | Vendor confirmed | Container Station Ollama tutorial for QTS/QuTS hero x86 NAS. |
| Open WebUI | Yes | Vendor confirmed | QNAP Open WebUI tutorial, QTS 5.2 / QuTS hero h5.2+. |
| RAG | Limited | Unverified | Qsirch RAG Search (beta) exists; not confirmed for this model. |
| AI search | Yes | Vendor confirmed | Qsirch AI Semantic Search: 64-bit x86, 5.0.1+, 8GB RAM. AI Mode needs a 16GB+ VRAM GPU, none on this model's list. |
| GPU expansion | Limited | Vendor confirmed | PCIe Gen4 x16 slot, 185 mm card limit; official list only GT 1030, Quadro P620/P1000, RTX A400 4GB. |
| Hardware acceleration | Yes | Vendor confirmed | UHD Graphics 730 transcoding; Hailo-8 M.2 (26 TOPS) on AI accelerator list. |
| AI photos | Yes | Vendor confirmed | QuMagie AI-driven smart photo and video albums. |
| AI video | Yes | Vendor confirmed | QVR Face listed under QTS. |
| Surveillance AI | Yes | Vendor confirmed | QVR Surveillance 2 free + 6 on registration; QVR Pro 8 free (QTS). |
Plan on upgrading. 32GB is fitted as standard, while the TVS-h674T accepts 64GB of DDR4 SODIMM, which is the difference between models up to the 14B class, with 32B class models a tight fit and 32B class models comfortably, and 70B class models at 4-bit with little headroom (Estimated).
Our estimate for the biggest model that fits in 64GB is about 93B parameters at 4-bit, after setting aside 8GB for the system. Long context windows reduce that figure (Estimated).
Yes, through a PCIe Gen4 x16 + PCIe Gen4 x4 (Thunderbolt 4 card preinstalled); cards up to 185 mm. That is the single biggest upgrade for local AI on the TVS-h674T: model layers move into fast graphics memory and replies speed up dramatically. Card size and power are the constraints (250W supply).
As the storage half of a RAG setup it works well; as the model host it is limited. Small embedding models run fine on the TVS-h674T, while the answering model needs more compute than it has.
The manufacturer also provides AI search across your files (documented by the manufacturer), which covers simple document questions without setting up your own stack.
For network access it has 2 x 2.5GbE. Enough for light use; large imports will take a while.
| Configuration | RAM | SSD | Notes |
|---|---|---|---|
| TVS-h674T-i5-32G | 32GB | None | Only configuration listed |
The closest QNAP model by AINAS Score. Only the specifications that differ are listed.
Best fit: people who want a private chat assistant or coding model at home without sending data to a cloud service. That is where the TVS-h674T scores highest (Local LLM 52/100), followed by RAG (52/100).
Less suited to teams moving large files over the network every day.
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.
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, and the PCIe Gen4 x16 + PCIe Gen4 x4 (Thunderbolt 4 card preinstalled); cards up to 185 mm can take a faster network card. 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.