96GB max RAM · 5 bays · 10GbE
AINAS Score 62
No verified UK price
View
Can the QNAP TVS-h874T run local AI?
The QNAP TVS-h874T can run small local models, with limits. Its 12th Gen Intel Core i7 (12-core 8P+4E, 20 threads); i9 (16-core 8P+8E, 24 threads) on i9-64G and 64GB memory ceiling suit 32B class models comfortably, and 70B class models at 4-bit with little headroom (Estimated), so treat it as a storage-first NAS that can host light AI tools.
It also has a GPU path (PCIe x16 slot), so a graphics card can be added later for much faster inference.
Local LLM support is documented by the manufacturer.
The TVS-h874T is a high-end eight-bay desktop NAS with a 12th-generation Core i7 or i9, up to 64GB of memory and Thunderbolt 4 built in. On paper it looks like an AI machine. In practice QNAP's official GPU list for it stops at a 4GB card, because the PCIe x16 slot only takes cards up to 185mm and the power supply is 350W.
So the AI story rests on the CPU. QNAP documents Ollama and Open WebUI on its x86 systems, its Qsirch semantic search runs here, and QuMagie and the surveillance suite handle photo and video recognition well. The i9 version with 64GB can hold 32B class models, but replies will be slow without a capable GPU.
It is best for creative studios and power users who want fast local storage over Thunderbolt and 10GbE with a few private AI tools alongside. If running language models is the main job, a system with a full-size GPU slot or a newer AI processor will do far more for the money.
Amazon UK
TVS-h874T-i7-32G
£3,834
Verified
In stock
View dealAmazon UK
TVS-h874T-i9-64G
No current price
Not yet verified
Out of stock
Check price on Amazon UKProduct 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). Officially supported GPUs are 4GB or less, so inference is mostly 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; on-prem RAG documented only for GPU-equipped TS-h1290FX. 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 GPU list. |
| GPU expansion | Limited | Vendor confirmed | PCIe Gen4 x16 slot but 185 mm card limit and 350W PSU; official list only GT 1030, Quadro P620/P1000, RTX A400 4GB. |
| Hardware acceleration | Yes | Vendor confirmed | UHD Graphics 770 transcoding; Coral Edge TPU (4 TOPS) and 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 QVR Pro (QTS). |
| Surveillance AI | Yes | Vendor confirmed | QVR Surveillance 2 free + 6 on registration; QVR Pro 8 free (QTS). |
The TVS-h874T ships with 32GB of DDR4 SODIMM and supports up to 64GB. Upgrading to the maximum lifts the model ceiling from models up to the 14B class, with 32B class models a tight fit to 32B class models comfortably, and 70B class models at 4-bit with little headroom (both Estimated).
As a rule of thumb, a 4-bit model needs about 0.6GB per billion parameters plus room for context. After leaving around 8GB for the NAS operating system, 64GB leaves space for a model of roughly 93B parameters at most (Estimated).
Yes. The TVS-h874T has a PCIe Gen4 x16 + PCIe Gen4 x4 (Thunderbolt 4 card preinstalled); cards up to 185 mm that can take a graphics card. A discrete GPU with its own memory runs models far faster than CPU inference and lets the NAS serve several users at once. Check card length, height and power draw against the chassis and the 350W power supply first.
With limits. The TVS-h874T 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.
The manufacturer also provides AI search across your files (documented by the manufacturer), which covers simple document questions without setting up your own stack.
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 |
|---|---|---|---|
| TVS-h874T-i7-32G | 32GB | None | Core i7, 12 cores / 20 threads |
| TVS-h874T-i9-64G | 64GB | None | Core i9, 16 cores / 24 threads; already at the 64GB maximum |
The closest QNAP model by AINAS Score. Only the specifications that differ are listed.
The TVS-h874T scores best for RAG (59/100) and Home Lab (59/100). It suits anyone building private search and question answering over their own documents.
It is a weaker fit for teams moving large files over the network every day.
Other AI Ready 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.