64GB max RAM · 8 bays · 2.5GbE
AINAS Score 58
No verified price

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 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.
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.
Each capability shows how it was confirmed: Verified by AINAS, Vendor confirmed, Community confirmed or Unverified.
| Capability | Supported | Evidence | Note |
|---|---|---|---|
| Local LLM | Limited | Community confirmed | CPU-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 | Yes | Community confirmed | Not 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 | Yes | Community confirmed | Guide documents Open WebUI alongside Ollama on Synology DSM via Container Manager; same DSM platform, not this exact unit. |
| RAG | Limited | Unverified | No 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 | No | Vendor confirmed | GPU-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 | No | Vendor confirmed | 2x 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 | No | Vendor confirmed | Spec lists a hardware encryption engine only; no integrated GPU, NPU or hardware transcoding listed. |
| AI photos | Yes | Vendor confirmed | Synology Photos face and object recognition listed for this model (on-device, CPU). |
| AI video | Limited | Vendor confirmed | No 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 | Yes | Vendor confirmed | Surveillance Station supported, up to 160 IP cameras (1080p H.264, 2800 FPS); 2 free licences, more require purchase. |
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.
| Model | Best quantization | Runs? | Memory needed | Expected performance | Verification |
|---|---|---|---|---|---|
| Llama 3.2 3BLlama, 3.21B | Q8 | Yes | 13GB | Not measured | Estimated |
| Llama 3.1 8BLlama, 8.03B | Q8 | Yes | 19GB | Not measured | Estimated |
| Qwen3 8BQwen, 8.19B | Q8 | Yes | 19GB | Not measured | Estimated |
| Gemma 3 12BGemma, 11.8B | Q8 | Yes | 24GB | Not measured | Estimated |
| Qwen3 14BQwen, 14.8B | Q8 | Yes | 28GB | Not measured | Estimated |
| Phi-4 14BPhi, 14.7B | Q8 | Yes | 28GB | Not measured | Estimated |
| Mistral Small 3 24BMistral, 23.6B | Q8 | Yes | 38GB | Not measured | Estimated |
| Gemma 3 27BGemma, 27B | Q8 | Yes | 44GB | Not measured | Estimated |
| Qwen3 30B A3BQwen, 30.5B | Q8 | Yes | 47GB | Not measured | Estimated |
| Qwen3 32BQwen, 32.8B | Q8 | Yes | 50GB | Not measured | Estimated |
| DeepSeek-R1 32B (Qwen distill)DeepSeek, 32.8B | Q8 | Yes | 50GB | Not measured | Estimated |
| Llama 3.3 70BLlama, 70.6B | Q8 | Yes | 98GB | Not measured | Estimated |
| Llama 4 Scout 17Bx16ELlama, 109B | Q4 | Yes | 89GB | Not measured | Estimated |
| Qwen2.5 72BQwen, 72.7B | Q8 | Yes | 101GB | Not measured | Estimated |
| Mistral Large 2 123BMistral, 123B | Q5 | Yes | 112GB | Not measured | Estimated |
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.
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 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 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 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.
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.
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.
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 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.
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.
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.
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.
| Configuration | RAM | SSD | Notes |
|---|---|---|---|
| SA3610 16GB ECC | 16GB | None |
The closest Synology model by bay count and AINAS Score. Only the specifications that differ are listed.
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.
Other AI Ready systems closest in overall score.
Workloads it suits
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.
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.
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.
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.
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.
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.
Yes. Ollama support is confirmed by community reports. See the capability table above for the source.
Yes. Open WebUI support is confirmed by community reports. 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.
No. Hardware acceleration support is documented by the manufacturer. See the capability table above for the source.
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.
Every field records its source. Specifications were last checked on . Spot an error? Send a correction with a manufacturer link.