64GB max RAM · 6 bays · 2 x 10GbE
AINAS Score 52
£919.99
Amazon UK · Verified

AI ReadySynologyDiscontinued
Why AI Ready: Intel Xeon D-1541 with no iGPU or NPU, two PCIe Gen3 x8 slots (x8 link) and a 64GB memory ceiling, which meets the AI Ready line for Xeon under 128GB. Synology's card list names network and M.2 cards, not GPUs.
Updated
Can the Synology RS3621xs+ run local AI?
Partly. The Synology RS3621xs+ runs local models on Intel Xeon D-1541 alone, and its 64GB ceiling allows 32B class models comfortably, and 70B class models at 4-bit with little headroom (Estimated), but replies will be slow without graphics acceleration.
No graphics card can be fitted, which keeps every model on the CPU.
Local LLM support is confirmed by community reports.
The RS3621xs+ suits small businesses and home labs that want a 12-bay rackmount NAS with Docker and virtual machines, and want to try local AI on the side. It has an Intel Xeon D-1541 with 8 cores, 8GB of DDR4 ECC UDIMM memory that expands to 64GB, and two 10GbE ports plus four 1GbE ports. Two PCIe Gen3 x8 slots take 25GbE or 10GbE network cards. Container Manager and Virtual Machine Manager are both supported. Surveillance Station covers up to 90 IP cameras. Synology Photos face and object recognition is vendor confirmed. The AINAS Score is 52. It comes with a 5 year warranty.
The RS3621xs+ is discontinued, and it has no GPU path. Synology says unlisted models do not support GPU cards, and this one is not on the list. There is also no NPU or integrated graphics, so any local model runs on the CPU only. Buyers who want fast local LLM work, GPU-powered AI search or hardware transcoding are affected. They should look for a system with a supported GPU slot, an NPU or integrated graphics, and a memory ceiling above 64GB. Anyone planning to standardise on one rackmount model across several sites should also weigh its discontinued status.
No verified price
We have not verified a listing for the Synology RS3621xs+ 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. 64 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 90 IP cameras (1080p H.264, 2250 FPS); 2 free licences, more require purchase. |
Calculated from the RS3621xs+'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 | Q4 | Yes | 60GB | Not measured | Estimated |
| Llama 4 Scout 17Bx16ELlama, 109B | None fits | No | 89GB at Q4 | Not measured | Estimated |
| Qwen2.5 72BQwen, 72.7B | Q3 | Yes | 54GB | Not measured | Estimated |
| Mistral Large 2 123BMistral, 123B | Q2 | Yes | 62GB | Not measured | Estimated |
One verdict per workload, from the RS3621xs+'s use-case scores and capability rows. Unknown means we cannot confirm it, not that it probably works.
The RS3621xs+ is an acceptable local LLM host, with limits. Ollama runs CPU-only in Container Manager (community confirmed), the guide covers the same DSM platform rather than this exact unit, and there is no GPU or NPU.
Private RAG is workable but not turnkey. Synology offers no local RAG on this model, and Open WebUI document chat through Docker is plausible but unverified here, though Open WebUI with Ollama is community confirmed.
AI search is a poor fit. Vendor information says GPU-powered AI Search in Synology Drive is limited to other models, and the RS3621xs+ is not among them.
AI photos is a good fit. Synology Photos face and object recognition is listed for this model by the vendor, and it runs on the CPU.
Surveillance is a good fit. Surveillance Station supports up to 90 IP cameras, with 2 free licences and more by purchase, and on-camera AI from Synology BC500 cameras is usable, though there is no deep video analytics on the NAS.
Home lab use is a good fit. It supports Docker and virtual machines, has 12 bays and a Xeon D-1541 with 8 cores, and its memory is ECC and expandable to 64GB.
Business use is a good fit. It has 12 bays, ECC memory, two 10GbE ports and a 5 year warranty, plus PCIe slots that take 25GbE cards from the Synology list.
Creative AI is only acceptable. GPU expansion and hardware acceleration are both vendor confirmed as unsupported, so work stays on the CPU, and local LLM support is limited.
Out of the box the RS3621xs+ has 8GB; the official ceiling is 64GB of DDR4 ECC UDIMM with ECC support. A memory upgrade is the cheapest way to make it more useful for AI.
Working backwards from 64GB: reserve about 8GB for the operating system and storage services, and at roughly 0.6GB per billion parameters at 4-bit, the largest model that fits is around 93B (Estimated).
ECC support protects against silent memory errors on a box that runs around the clock.
There is no supported way to add a GPU to the RS3621xs+: no PCIe slot and no OCuLink. Inference runs on the CPU, so keep to small models.
For a personal library, yes. A compact embedding model and a small chat model will run, but the RS3621xs+ is better as the document store behind a RAG system whose model runs on stronger hardware.
Built-in networking: 2 x 10GbE + 4 x 1GbE. Plenty for a shared knowledge base with several users.
| Configuration | RAM | SSD | Notes |
|---|---|---|---|
| RS3621xs+ 8GB ECC | 8GB | None |
The closest Synology model by bay count and AINAS Score. Only the specifications that differ are listed.
Its strongest AINAS profiles are Home Lab at 64 and Business at 62, which points to home lab owners who want one box for storage, containers, media and a few AI services.
Look elsewhere if you are buyers who expect to add a graphics card later, or buyers who want a model with a long support life ahead.
Other AI Ready systems closest in overall score.
Workloads it suits
Yes at Q4, with no headroom to spare. Estimated: Llama 3.3 70B needs 43GB at Q4, which fits within the 64GB ceiling. At Q8 it needs 75GB and does not fit (Estimated). The system has no GPU or NPU, so Ollama runs on the CPU only, and the community guide covers the same DSM platform, not this exact unit.
64GB is the maximum. The RS3621xs+ ships with 8GB of DDR4 ECC UDIMM memory, and the memory is expandable. The 64GB ceiling limits the largest models. Llama 4 Scout 17Bx16E does not fit at Q4 (Estimated), and Qwen2.5 72B is marginal at Q4 (Estimated), meaning it loads with little headroom.
Yes. The RS3621xs+ uses DDR4 ECC UDIMM memory, and the 8GB it ships with is ECC. The memory is expandable to 64GB. ECC helps protect data integrity in business, virtual machine and home lab use, where long uptime matters.
No. It has two PCIe Gen3 x8 slots, but Synology says unlisted models do not support GPU cards, and this model is not on the list. The vendor card list names network cards (25GbE and 10GbE) and M.2 adapters, not GPUs. Look for a model with a listed GPU path instead.
No. It has no built-in M.2 slots, so the NVMe count is zero. M.2 storage is possible only through an optional PCIe adapter, and Synology lists the E10M20-T1 and the M2D20. Either one takes up one of the two PCIe Gen3 x8 slots.
Yes. The RS3621xs+ runs Synology DSM, with Container Manager for Docker and Virtual Machine Manager for virtual machines. The 8-core Intel Xeon D-1541 and up to 64GB of DDR4 ECC UDIMM give room for several containers and virtual machines next to file storage. AI containers run on the CPU only, because there is no GPU, NPU or integrated graphics, so larger models load but answer slowly compared with a GPU system (Estimated).
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.