16GB max RAM · 2 bays · 2.5GbE
AINAS Score 28
No verified UK price
View
Can the Synology DS923+ run local AI?
Partly. The Synology DS923+ runs local models on AMD Ryzen R1600 alone, and its 32GB ceiling allows models up to the 14B class, with 32B class models a tight fit (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 DS923+ is the 2022 four-bay Synology that the DS925+ replaced, and Synology now lists it as phased out. We moved it from Traditional to AI Capable after checking the specification: it has the same two-core Ryzen R1600 and 32GB ECC ceiling as the current DS725+, plus two M.2 slots and Container Manager support.
That puts it in the same position as the DS725+ for AI: small models in Ollama on the CPU, slowly, and AI Console as a bridge to cloud or self-hosted models elsewhere. There is no integrated graphics, no NPU and no GPU path.
It does have one advantage over its replacement: a network upgrade slot for an optional 10GbE module, which the DS925+ dropped. If you already own one, upgrade the memory and the network card before you replace it. If you are buying, check prices carefully against the DS925+ and the DS1525+, which offer newer hardware for similar money.
Not currently on Amazon UK
We could not find a UK listing for the Synology DS923+ from a retailer we track. The specifications below stand on their own; a price appears here as soon as a UK 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 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; 2-core R1600 suits only small (1B to 3B) models. Needs RAM upgrade beyond 4 GB base. |
| Ollama | Yes | Community confirmed | Not in Package Center; ollama/ollama container runs in Container Manager on DSM (CPU only). |
| Open WebUI | Yes | Community confirmed | Open WebUI container documented on Synology DSM pointing at Ollama on port 11434. |
| RAG | Limited | Unverified | No Synology local RAG for this model; Open WebUI document chat plausible via Docker but not verified on this unit. AI Console only bridges to cloud or OpenAI-compatible APIs. |
| AI search | No | Vendor confirmed | Synology AI Search in Drive uses GPU-powered embedding/OCR models only on supported systems with a GPU (FS/26-series list); this model is not listed. |
| GPU expansion | No | Vendor confirmed | No PCIe slot usable for a GPU; no OCuLink or USB4. |
| Hardware acceleration | No | Community confirmed | Ryzen R1600 has no integrated GPU and no NPU; no hardware transcoding or AI acceleration. |
| AI photos | Yes | Vendor confirmed | Synology Photos facial recognition and object recognition listed in product spec (on-device, CPU). |
| AI video | Limited | Community confirmed | No on-NAS deep video analytics (DVA models only); Surveillance Station can use edge AI from Synology BC500/TC500 cameras. |
| Surveillance AI | Yes | Vendor confirmed | Surveillance Station supported, up to 40 IP cameras (1080p H.264); 2 free licences, more require purchase. |
Out of the box the DS923+ has 4GB; the official ceiling is 32GB of DDR4 ECC SODIMM with ECC support. A memory upgrade is the cheapest way to make it more useful for AI.
Working backwards from 32GB: 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 40B (Estimated).
ECC memory support is a plus for always-on systems that also hold important files.
There is no supported way to add a GPU to the DS923+: 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 DS923+ is better as the document store behind a RAG system whose model runs on stronger hardware.
Built-in networking: 2 x 1GbE. Adequate for a household, slower for bulk indexing.
| Configuration | RAM | SSD | Notes |
|---|---|---|---|
| 4GB | 4GB | None | 4 GB DDR4 ECC SODIMM (1x 4 GB), 2 slots, max 32 GB |
The closest Synology model by AINAS Score. Only the specifications that differ are listed.
Its strongest AINAS profiles are Business at 32 and Home Lab at 31, which points to small offices that need shared storage with private AI tools and room to grow.
Look elsewhere if you are buyers who expect to add a graphics card later, or teams moving large files over the network every day.
Other AI Capable systems closest in overall score.
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 confirmed by community reports. See the capability table above for the source.
It has 2 x 1GbE built in, and the 1x PCIe Gen3 x2 network upgrade slot (optional E10G22-T1-Mini 10GbE RJ-45 module) can take a faster network card. The fastest port is 1GbE.
Every field records its source. Specifications were last checked on . Spot an error? Send a correction with a manufacturer link.