AINAS
Synology SA3610 12-bay NAS

Synology SA3610

AI ReadySynology

Why AI Ready: Intel Xeon D-1567 with no NPU, two PCIe Gen3 x8 slots but no Synology-documented GPU support, and a 128 GB memory ceiling, so ready rather than native.

Updated

Can the Synology SA3610 run local AI?

Only lightly. Expect 70B class models at higher-quality quantization, or large mixture-of-experts models at 4-bit (Estimated) on the Synology SA3610: Intel Xeon D-1567 does the work with up to 128GB of memory, which is fine for experiments rather than a daily assistant.

Without any GPU option, the processor carries the whole inference load.

Local LLM support is confirmed by community reports.

The short answer

The SA3610 suits businesses and home lab users who want a 12-bay rackmount Synology for storage first, with CPU-only AI as an extra. It has an Intel Xeon D-1567 with 12 cores, 16GB of DDR4 ECC RDIMM expandable to 128GB, 2 x 10GbE and 4 x 1GbE. Docker and virtual machines are both supported. Synology Photos face and object recognition is vendor confirmed, and Surveillance Station is vendor confirmed for up to 160 IP cameras. A 5-year warranty and a 550W power supply complete the package. On memory alone, models up to Mistral Large 2 123B load at Q4 (Estimated), though with no GPU everything runs on the CPU.

The SA3610 has no GPU path. It has two PCIe Gen3 x8 slots, but Synology does not list the model for GPU cards, and the vendor says unlisted models do not support them. There is also no NPU and no hardware acceleration. Anyone planning heavier local LLM work, image generation or GPU-assisted AI search should look elsewhere. They need a system with a documented GPU expansion path, or an integrated GPU or NPU, plus enough PCIe lanes and power for a card. Buyers who only need storage, photo recognition, surveillance and containers will not be affected.

Current offers

No verified price

We have not verified a listing for the Synology SA3610 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 Xeon D-1567
Source: Manufacturer
Included RAM
16GB DDR4 ECC RDIMM
Source: Manufacturer
Maximum RAM
128GB ECC
Source: Manufacturer
Networking
2 x 10GbE + 4 x 1GbE
Source: Manufacturer
PCIe
2x PCIe Gen3 x8 slots (x8 link); Synology-listed cards: E25G30-F2 (25GbE), E10G30-F2 and other 10GbE NICs, E10M20-T1 and M2D20 (M.2)
Source: Manufacturer
GPU expansion
None
Source: Official docs
Power supply
550W
Source: Manufacturer
OS
Synology DSM
Source: Manufacturer
Docker
Yes
VM support
Yes
Released
2023
Segment
Enterprise

Can the SA3610 run local LLMs?

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

CapabilitySupportedEvidenceNote
Local LLMLimitedCommunity confirmedCPU-only Ollama via Container Manager on x86 DSM models. 128 GB memory ceiling, no GPU or NPU. Guide covers the same DSM platform, not this exact unit.
Ollama YesCommunity confirmedNot in Package Center; ollama/ollama container runs in Container Manager on x86 Synology DSM (CPU only). Guide covers the same DSM platform, not this exact unit.
Open WebUI YesCommunity confirmedGuide documents Open WebUI alongside Ollama on Synology DSM via Container Manager; same DSM platform, not this exact unit.
RAGLimitedUnverifiedNo Synology local RAG on this model. AI Console bridges to third-party AI providers. Open WebUI document chat via Docker plausible but not verified on this unit.
AI search NoVendor confirmedGPU-powered AI Search in Synology Drive is limited to FS3420, FS6420 and 26-series rack models per the AI Console 2.0 and AI Runtime 1.0 betas; this model is not listed.
GPU expansion NoVendor confirmed2x PCIe Gen3 x8 slots (x8 link) exists but this model is not on the Synology GPU card list, which says unlisted models do not support GPU cards.
Hardware acceleration NoVendor confirmedSpec lists a hardware encryption engine only; no integrated GPU, NPU or hardware transcoding listed.
AI photos YesVendor confirmedSynology Photos face and object recognition listed for this model (on-device, CPU).
AI videoLimitedVendor confirmedNo on-NAS deep video analytics (DVA series only). Surveillance Station can use on-camera AI people and vehicle detection from Synology BC500 cameras.
Surveillance AI YesVendor confirmedSurveillance Station supported, up to 160 IP cameras (1080p H.264, 2800 FPS); 2 free licences, more require purchase.

What AI models can the SA3610 run?

Calculated from the SA3610'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, 70.6BQ8Yes98GBNot measuredEstimated
Llama 4 Scout 17Bx16ELlama, 109BQ4Yes89GBNot measuredEstimated
Qwen2.5 72BQwen, 72.7BQ8Yes101GBNot measuredEstimated
Mistral Large 2 123BMistral, 123BQ5Yes112GBNot measuredEstimated

Workload fit

One verdict per workload, from the SA3610's use-case scores and capability rows. Unknown means we cannot confirm it, not that it probably works.

Local LLMOK

The SA3610 is an acceptable local LLM host, with limits. Support is marked limited and community confirmed: CPU-only Ollama runs in Container Manager, with no GPU or NPU, and the guide covers the same platform rather than this exact unit.

Private RAGOK

Private RAG is workable but not confirmed on this unit. Ollama and Open WebUI are community confirmed through Docker, yet Synology offers no local RAG here, and document chat through Open WebUI is marked Unverified.

AI searchPoor fit

AI search is a poor fit on the SA3610. Synology confirms that GPU-powered AI Search in Drive is limited to other models, and this one is not among them.

AI photosGood fit

AI photos work well here. Synology Photos face and object recognition is vendor confirmed for this model, running on the CPU without needing a GPU or NPU.

SurveillanceGood fit

Surveillance is a strong use for the SA3610. Surveillance Station is vendor confirmed for up to 160 IP cameras, with 2 free licences and more by purchase. On-NAS deep video analytics are not offered.

Home labGood fit

The SA3610 is a good home lab base. Docker and virtual machines are both supported, and it has 12 bays, ECC memory, 2 x 10GbE and two PCIe Gen3 x8 slots for expansion cards.

BusinessGood fit

Business use suits the SA3610 well. It has ECC RDIMM memory, 12 bays, 2 x 10GbE, a 5-year warranty and a Synology DSM platform in a rackmount form factor.

Creative AIOK

Creative AI is workable only on the CPU. GPU expansion and hardware acceleration are both vendor confirmed as unsupported, so any generation work depends on the Xeon and up to 128GB of memory.

How much RAM does the SA3610 support?

Plan on upgrading. 16GB is fitted as standard, while the SA3610 accepts 128GB of DDR4 ECC RDIMM, ECC included, which is the difference between 7B to 8B class models and 70B class models at higher-quality quantization, or large mixture-of-experts models at 4-bit (Estimated).

Our estimate for the biggest model that fits in 128GB is about 200B parameters at 4-bit, after setting aside 8GB for the system. Long context windows reduce that figure (Estimated).

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

Can you add a GPU to the SA3610?

A graphics card is not an option on the SA3610, which has neither a PCIe slot nor OCuLink. Inference runs on the CPU, so keep to small models.

Is the SA3610 suitable for RAG?

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 SA3610, while the answering model needs more compute than it has.

For network access it has 2 x 10GbE + 4 x 1GbE. Fast enough that the network will not be the bottleneck.

Limitations

  • No GPU path: the two PCIe Gen3 x8 slots exist, but Synology does not list the SA3610 for GPU cards, so all AI work runs on the CPU.
  • No NPU and no integrated GPU, and Synology lists only a hardware encryption engine, so hardware acceleration and transcoding are not supported.
  • No built-in M.2 slots. M.2 storage needs an optional PCIe adapter, which uses one of the two x8 slots.
  • Only 16GB is fitted in the SA3610 16GB ECC configuration. Llama 3.3 70B needs a memory upgrade to fit, and Qwen3 235B A22B stays out of reach even at the 128GB ceiling (Estimated).
  • Local AI capabilities rest on community guides covering the same DSM platform, not this exact unit, and Private RAG is Unverified.

Which SA3610 configurations are sold?

ConfigurationRAMSSDNotes
SA3610 16GB ECC16GBNone

How is the SA3610 different from the SA3410?

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

  • Processor: Intel Xeon D-1567 on the SA3610, Intel Xeon D-1541 on the SA3410
  • CPU cores: 12 on the SA3610, 8 on the SA3410
  • AINAS Score: 58 on the SA3610, 57 on the SA3410

See the full Synology SA3410 page

Who should buy the SA3610?

Best fit: home lab owners who want one box for storage, containers, media and a few AI services. That is where the SA3610 scores highest (Home Lab 70/100), followed by Business (67/100).

Less suited to buyers who expect to add a graphics card later.

What are the alternatives to the SA3610?

Other AI Ready systems closest in overall score.

45Drives HL8

45Drives HL8

45Drives

AI Ready

64GB max RAM · 8 bays · 2.5GbE

AINAS Score 58

No verified price

View
QNAP TVS-h674

QNAP TVS-h674

QNAP

AI Ready

64GB max RAM · 6 bays · 2 x 2.5GbE

AINAS Score 58

No verified price

View
QNAP TVS-h874T

QNAP TVS-h874T

QNAP

AI Ready

64GB max RAM · 8 bays · 2 x 2.5GbE

AINAS Score 58

£3,834

Amazon UK · Verified

View

Where does the SA3610 rank?

Workloads it suits

Common questions

Can the SA3610 run Mistral Large 2 123B?

Yes at Q4, as an estimate. Mistral Large 2 123B needs 73GB at Q4, which fits within the 128GB maximum memory (Estimated). At Q8 it needs 130GB and does not fit (Estimated). It would run on the CPU only, as there is no GPU path.

How much memory does the SA3610 take?

Up to 128GB. The SA3610 ships with 16GB of DDR4 ECC RDIMM and the memory is expandable. Because the memory is ECC RDIMM, you need compatible registered ECC modules. The 16GB configuration is the one we list.

Does the SA3610 support ECC memory?

Yes. The SA3610 uses DDR4 ECC RDIMM, and ECC is part of the specification. That suits storage and business workloads where memory errors matter, and it is expandable from the included 16GB to 128GB.

Can the SA3610 take a graphics card?

No. It has two PCIe Gen3 x8 slots, but Synology's GPU card list does not include this model, and the vendor says unlisted models do not support GPU cards. Synology-listed cards are 25GbE and 10GbE network adapters and M.2 adapters.

Does the SA3610 have M.2 slots?

No. The SA3610 has 0 built-in M.2 slots, and its 12 bays hold the storage. M.2 drives need an optional adapter from Synology's card list, the E10M20-T1 or M2D20, fitted in one of the two PCIe Gen3 x8 slots. Those same slots carry any 25GbE upgrade such as the E25G30-F2, so it pays to plan which cards go where, with the two 10GbE ports built in covering most needs.

Does the SA3610 run Docker?

Yes. The SA3610 is on Synology's Container Manager applied-models list. Community guides show CPU-only Ollama and Open WebUI running in containers on this DSM platform, though they cover the platform rather than this exact unit. Virtual machines are supported too.

Does Ollama work on the SA3610?

Yes. Ollama support is confirmed by community reports. See the capability table above for the source.

Can you install Open WebUI on the SA3610?

Yes. Open WebUI support is confirmed by community reports. See the capability table above for the source.

Can the SA3610 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 SA3610 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 SA3610?

No. Hardware acceleration support is documented by the manufacturer. See the capability table above for the source.

What networking does the SA3610 have?

It has 2 x 10GbE + 4 x 1GbE built in, and the 2x PCIe Gen3 x8 slots (x8 link); Synology-listed cards: E25G30-F2 (25GbE), E10G30-F2 and other 10GbE NICs, E10M20-T1 and M2D20 (M.2) can take a faster network card. The fastest port is 2 x 10GbE.

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.