AINAS
QNAP TS-473A 4-bay NAS

QNAP TS-473A

AI CapableQNAP

Why AI Capable: Ryzen V1500B (2018 embedded) is not a current CPU; its PCIe Gen3 x4 slots take only low-profile GPUs up to 6GB on QNAP's list.

Updated

Can the QNAP TS-473A run local AI?

Yes, the QNAP TS-473A can run local language models. It pairs AMD Ryzen Embedded V1500B with up to 64GB of memory, which suits 32B class models comfortably, and 70B class models at 4-bit with little headroom (Estimated).

It also has a GPU path (PCIe x4 slot), so a graphics card can be added later for much faster inference.

Local LLM support is documented by the manufacturer.

The short answer

The TS-473A suits a buyer who wants a four-bay QNAP NAS that can also run local AI containers on a budget of effort rather than hardware. It takes up to 64GB of DDR4 SODIMM with ECC supported, ships with 8GB, and runs Docker and virtual machines on QTS or QuTS hero. Two PCIe Gen3 x4 slots accept a low-profile NVIDIA card, and QNAP lists cards up to the RTX 3050 LP 6G. Ollama and Open WebUI are vendor confirmed. On memory alone, Llama 3.3 70B fits at Q4 (Estimated). It also has 4 bays, 2 M.2 slots and 2 x 2.5GbE.

The main limit is the GPU path. The Ryzen Embedded V1500B has no integrated GPU and no NPU, so any acceleration needs an add-in card, and the cards QNAP lists top out at 6GB. Buyers who want fast inference on mid-size or large models should look for a system with a much larger GPU memory ceiling, or a built-in NPU with a higher TOPS figure. Network buyers should also note that the onboard ports are 2.5GbE only, so 10GbE needs a PCIe card. Memory is less of a constraint, since up to 64GB of DDR4 SODIMM holds large models, but any model too big for a 6GB card runs on the 4-core CPU.

Current offers

  • Amazon US

    TS-473A-8G

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

    $887.84

    Verified

    In stock

    Buy on Amazon

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.

Price history

Current
$887.84
30-day average
$900.26
90-day low
$887.83
All-time tracked low
$887.83
$887.00$897.00$906.0020 AugToday
Last in-stock Amazon US price we verified each day. Dashed line: 30-day average. Days out of stock are not drawn as prices.

Key specifications

CPU
AMD Ryzen Embedded V1500B
Source: Manufacturer
Included RAM
8GB DDR4 SODIMM
Source: Manufacturer
Maximum RAM
64GB ECC
Source: Manufacturer
Networking
2 x 2.5GbE
Source: Manufacturer
PCIe
2x PCIe Gen3 x4
Source: Manufacturer
GPU expansion
PCIe x4 slot
Source: Official docs
Power supply
250W
Source: Manufacturer
OS
QTS 6.1.0 / QuTS hero h6.1.0
Source: Manufacturer
Docker
Yes
VM support
Yes
Released
2021
Segment
Desktop

Can the TS-473A run local LLMs?

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

CapabilitySupportedEvidenceNote
Local LLM YesVendor confirmedQNAP Ollama guide (x86, optional NVIDIA GPU from compatibility list). 64 GB RAM; GPUs up to RTX 3050 6GB, so small models on GPU.
Ollama YesVendor confirmedContainer Station Ollama tutorial for x86_64 QTS/QuTS hero.
Open WebUI YesVendor confirmedQNAP Open WebUI tutorial, QTS 5.2 / QuTS hero h5.2+.
RAGLimitedUnverifiedQsirch AI Knowledge Search (RAG) uses cloud LLMs; not confirmed for this model.
AI search YesVendor confirmedQsirch AI Semantic Search needs 64-bit x86 and 8 GB RAM.
GPU expansion YesVendor confirmedGPGPU list up to RTX 3050 LP 6G; product page: entry-level NVIDIA cards for video processing or VM passthrough.
Hardware accelerationLimitedVendor confirmedNo iGPU; add-in GPU for transcoding, QAI-M100/U100 (3 TOPS) and Coral M.2/USB Edge TPU on compatibility list.
AI photos YesVendor confirmedQuMagie AI-assisted photo management (people, things, places).
AI video YesUnverifiedSoftware spec page summary did not confirm QVR Face for this model (it is listed for sibling TS-873A).
Surveillance AI YesVendor confirmedQVR Pro 8 free channels (QTS); QVR Surveillance 2 free + 6 on registration.

What AI models can the TS-473A run?

Calculated from the TS-473A'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, 23.6BQ8Yes38GBNot measuredEstimated
Gemma 3 27BGemma, 27BQ8Yes44GBNot measuredEstimated
Qwen3 30B A3BQwen, 30.5BQ8Yes47GBNot measuredEstimated
Qwen3 32BQwen, 32.8BQ8Yes50GBNot measuredEstimated
DeepSeek-R1 32B (Qwen distill)DeepSeek, 32.8BQ8Yes50GBNot measuredEstimated
Llama 3.3 70BLlama, 70.6BQ4Yes60GBNot measuredEstimated
Llama 4 Scout 17Bx16ELlama, 109BNone fitsNo89GB at Q4Not measuredEstimated
Qwen2.5 72BQwen, 72.7BQ3Yes54GBNot measuredEstimated
Mistral Large 2 123BMistral, 123BQ2Yes62GBNot measuredEstimated

Workload fit

One verdict per workload, from the TS-473A's use-case scores and capability rows. Unknown means we cannot confirm it, not that it probably works.

Local LLMOK

The TS-473A is an acceptable local LLM host, not a fast one. Ollama is vendor confirmed through Container Station, and QNAP's notes say small models on GPU because listed cards stop at 6GB.

Private RAGOK

Private RAG is workable here, with one caveat. Ollama and Open WebUI are vendor confirmed, but the Qsirch RAG feature uses cloud LLMs and is unconfirmed for this model.

AI searchOK

AI search is a reasonable fit. Qsirch AI Semantic Search is vendor confirmed and needs 64-bit x86 and 8GB of RAM, which the 8GB included memory meets.

AI photosOK

AI photo management is covered. QuMagie is vendor confirmed for people, things and places, and runs on the x86 CPU without needing a graphics card.

SurveillanceOK

Surveillance works acceptably. QVR Pro offers 8 free channels on QTS and QVR Surveillance offers 2 free plus 6 on registration, both vendor confirmed, but QVR Face for this model is unconfirmed.

Home labOK

The TS-473A is an adequate home lab box. Docker and virtual machines are both supported, with GPU pass-through listed as working, and memory expands to 64GB across 2 SODIMM slots.

BusinessOK

Business use is acceptable. ECC memory is supported, there are 4 bays, a 250W power supply and a 3 year warranty, though the onboard networking is 2.5GbE only.

Creative AIOK

Creative AI is possible but limited. GPU expansion is vendor confirmed up to the RTX 3050 LP 6G, while hardware acceleration is marked limited because there is no iGPU and cards must be added.

How much RAM does the TS-473A support?

The TS-473A ships with 8GB of DDR4 SODIMM and supports up to 64GB with ECC. Upgrading to the maximum lifts the model ceiling from small models up to around 7B parameters 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).

ECC support protects against silent memory errors on a box that runs around the clock.

Can you add a GPU to the TS-473A?

Only a small one. The 2x PCIe Gen3 x4 in the TS-473A is sized for network and storage cards; low-profile GPUs are the limit.

Is the TS-473A suitable for RAG?

With limits. The TS-473A 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.

Limitations

  • No integrated GPU and no NPU. Acceleration needs an add-in card, and QNAP's compatibility list stops at the RTX 3050 LP 6G with 6GB, so large models cannot run on the GPU.
  • Onboard networking is 2 x 2.5GbE only. Faster 5GbE or 10GbE needs a PCIe card, which uses one of the two PCIe Gen3 x4 slots.
  • Only 8GB is included in the TS-473A-8G, so the larger Estimated fits on this page, such as Llama 3.3 70B at Q4, need a memory upgrade towards the 64GB ceiling first.
  • Qsirch RAG is marked limited and Unverified, and QVR Face is Unverified for this model, so neither should be counted as a confirmed feature.
  • The M.2 slots are PCIe Gen3 x1, and there is no Thunderbolt, USB4 or OCuLink, which limits fast external expansion.

Which TS-473A configurations are sold?

ConfigurationRAMSSDNotes
TS-473A-8G8GBNone

How is the TS-473A different from the TVS-h474?

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

  • Processor: AMD Ryzen Embedded V1500B on the TS-473A, Intel Core i3-12100 (4-core/8-thread, up to 4.3 GHz); Pentium Gold G7400 (2C/4T) on PT-8G on the TVS-h474
  • Integrated graphics: none on the TS-473A, Intel UHD Graphics 730 on the TVS-h474
  • ECC: yes on the TS-473A, no on the TVS-h474
  • GPU path: PCIe x4 slot on the TS-473A, PCIe x16 slot on the TVS-h474
  • AI class: AI Capable on the TS-473A, AI Ready on the TVS-h474
  • AINAS Score: 48 on the TS-473A, 56 on the TVS-h474

See the full QNAP TVS-h474 page

Who should buy the TS-473A?

The TS-473A scores best for Local LLM (51/100) and RAG (50/100). It suits people who want a private chat assistant or coding model at home without sending data to a cloud service.

It is a weaker fit for teams moving large files over the network every day.

What are the alternatives to the TS-473A?

Other AI Capable systems closest in price.

Where does the TS-473A rank?

Buying guides that list it

Common questions

Can the TS-473A run Llama 3.3 70B?

Yes, on memory alone. Llama 3.3 70B needs 43GB at Q4 and the TS-473A takes up to 64GB, so it fits at Q4 (Estimated). At Q8 it needs 75GB and does not fit (Estimated). Qwen2.5 72B is marginal at Q4 (Estimated). This is a memory calculation, not a benchmark, and the 6GB GPU limit means large models would run on the CPU.

How much memory does the TS-473A take?

Up to 64GB. It ships with 8GB of DDR4 SODIMM and has 2 slots, so the maximum is 2x 32GB. The memory sits in two slots rather than being soldered. ECC memory is supported. Added memory is what decides which models fit, so a larger kit widens the models listed on this page.

Can the TS-473A take a graphics card?

Yes. It has 2 PCIe Gen3 x4 slots and GPU expansion is vendor confirmed. QNAP's list includes the GTX 1650 LP, RTX 3050 LP 6G, Quadro P620 and P1000, and RTX A400 4GB. The cards are low-profile, and the largest listed has 6GB of memory.

Does the TS-473A have M.2 slots?

Yes, 2. They are M.2 2280 slots running at PCIe Gen3 x1. They sit alongside 4 SATA 3.5in bays. The x1 link suits caching or small fast volumes, and the slots do not use the PCIe expansion slots.

Can the TS-473A run Qwen3 32B?

Yes, on memory. Qwen3 32B needs 20GB at Q4 and 35GB at Q8, and both fit within the 64GB ceiling (Estimated). Neither fits on the 6GB cards QNAP lists for the PCIe slots, so the model would run on the 4-core Ryzen Embedded V1500B rather than the card. The TS-473A-8G comes with 8GB, so a memory upgrade comes first. Ollama and Open WebUI are vendor confirmed through Container Station. These are calculations, not benchmarks.

Does the TS-473A run Docker?

Yes. Docker is supported through Container Station on QTS 6.1.0 and QuTS hero h6.1.0. Virtual machines are also supported. QNAP's Ollama and Open WebUI guides are vendor confirmed for this x86 platform, so containers are the route for local AI software.

Does Ollama work on the TS-473A?

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

Can you install Open WebUI on the TS-473A?

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

Can the TS-473A 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 TS-473A 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 TS-473A?

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

What networking does the TS-473A have?

It has 2 x 2.5GbE built in, and the 2x PCIe Gen3 x4 can take a faster network card. 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.