32GB max RAM · 4 bays · 2 x 2.5GbE
AINAS Score 35
No verified price

AI CapableSynology
Why AI Capable: AMD Ryzen V1780B (4C/8T) with no NPU or iGPU, 32 GB max DDR4 ECC, and a PCIe Gen3 x8 (x4 link) slot that Synology supports only for NICs, so local AI is CPU-only small models via Container Manager.
Updated
Can the Synology DS1823xs+ run local AI?
Partly. The Synology DS1823xs+ runs local models on AMD Ryzen V1780B 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 DS1823xs+ is a storage-first Synology NAS for buyers who want 8 bays, DSM and a small amount of on-device AI. It has 2 M.2 slots, one 10GbE port and two 1GbE ports, and an AMD Ryzen V1780B with 4 cores. Memory is DDR4 ECC SODIMM, with 8GB included and a 32GB maximum, and you can upgrade it. Docker and virtual machines are supported. Synology Photos face and object recognition is vendor confirmed on this model, and Surveillance Station is supported with 2 free licences. Local models use the CPU only, through Container Manager. DeepSeek-R1 32B (Qwen distill) fits at Q4 (Estimated), but only after a memory upgrade. The AINAS Score is 35, which reflects a NAS that does file and camera work well and AI work modestly.
The limit that matters is the lack of a GPU path. The DS1823xs+ has no NPU and no integrated GPU. Its PCIe Gen3 x8 slot (x4 link) is listed by Synology only for 10GbE and 25GbE network cards, and GPU expansion is vendor confirmed as unsupported. Anyone planning serious local LLM work, private RAG over documents or creative AI should look elsewhere. Look for a system with a GPU-capable PCIe slot or OCuLink, or an NPU or integrated GPU, and a memory ceiling above 32GB. The 5-year warranty and ECC memory suit a business file server, but they do not change the CPU-only AI path.
Amazon UK
DS1823xs+ 8GB ECC
No current price
Checked , no price yet
Out of stock
Buy on AmazonAmazon US
DS1823xs+ 8GB ECC
Ships from the US; delivery and import charges shown at checkout
$2,049.99
Verified
In stock
Buy on AmazonProduct 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; no GPU or NPU, so small quantised models only. Needs RAM upgrade beyond base for 7B class. |
| 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 container alongside Ollama on Synology DSM via Container Manager. |
| RAG | Limited | Unverified | No Synology local RAG on this model. AI Console bridges to cloud AI providers or OpenAI-compatible endpoints (which could be self-hosted elsewhere). Open WebUI document chat via Docker plausible but not verified on this unit. |
| AI search | No | Vendor confirmed | AI Console 2.0 beta GPU-powered AI Search for Synology Drive is limited to FS3420, FS6420 and 26-series rack models; this model is not listed. |
| GPU expansion | No | Vendor confirmed | PCIe Gen3 x8 slot (x4 link) exists but Synology lists only 10GbE/25GbE NICs as optional accessories; no GPU support documented and the CPU has no iGPU. |
| Hardware acceleration | No | Vendor confirmed | Ryzen V1780B has no integrated GPU (AMD lists it without Radeon graphics) and no NPU; AES-NI encryption engine only. |
| AI photos | Yes | Vendor confirmed | Synology Photos face and object recognition supported on this model (on-device, CPU); also listed in product spec. |
| AI video | Limited | Vendor confirmed | No on-NAS deep video analytics (DVA series only). Surveillance Station can use on-camera AI people/vehicle detection from Synology BC500/TC500 cameras. |
| Surveillance AI | Yes | Vendor confirmed | Surveillance Station supported, up to 75 IP cameras (1080p H.264, 2100 FPS); 2 free licences, more require purchase. |
Calculated from the DS1823xs+'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 | Q4 | Yes | 25GB | Not measured | Estimated |
| Gemma 3 27BGemma, 27B | Q4 | Yes | 29GB | Not measured | Estimated |
| Qwen3 30B A3BQwen, 30.5B | Q4 | Yes | 31GB | Not measured | Estimated |
| Qwen3 32BQwen, 32.8B | Q4 | Yes | 32GB | Not measured | Estimated |
| DeepSeek-R1 32B (Qwen distill)DeepSeek, 32.8B | Q4 | Yes | 32GB | Not measured | Estimated |
| Llama 3.3 70BLlama, 70.6B | None fits | No | 60GB at Q4 | Not measured | Estimated |
| Llama 4 Scout 17Bx16ELlama, 109B | None fits | No | 89GB at Q4 | Not measured | Estimated |
| Qwen2.5 72BQwen, 72.7B | None fits | No | 65GB at Q4 | Not measured | Estimated |
| Mistral Large 2 123BMistral, 123B | None fits | No | 96GB at Q4 | Not measured | Estimated |
One verdict per workload, from the DS1823xs+'s use-case scores and capability rows. Unknown means we cannot confirm it, not that it probably works.
The DS1823xs+ is a poor choice for local LLM work. Support is limited and community confirmed, CPU-only through Container Manager with no GPU or NPU, and the notes say only small quantised models are realistic, with a RAM upgrade needed for 7B class.
Private RAG is a poor fit here. Synology offers no local RAG on this model, and Open WebUI document chat through Docker is plausible but unverified on this unit, so treat it as unconfirmed.
AI search is a poor fit on the DS1823xs+. Vendor documents confirm it is not supported: the GPU-powered AI Search for Synology Drive in the AI Console 2.0 beta is limited to other models, and this one is not among them.
AI photos work acceptably on the DS1823xs+. Synology Photos face and object recognition is vendor confirmed on this model, and it runs on the CPU on the device, since there is no NPU or GPU.
Surveillance is an acceptable use for the DS1823xs+. Surveillance Station is vendor confirmed for up to 75 IP cameras, with 2 free licences and paid licences for more, but on-NAS deep video analytics are not supported.
Home lab use is acceptable on the DS1823xs+. Docker and virtual machines are both supported, and it has 8 bays, 2 M.2 slots, a 10GbE port and DDR4 ECC memory that you can expand to 32GB.
Business use is acceptable on the DS1823xs+. It offers ECC memory, 8 bays, a 5 year warranty and a 250W power supply, and a PCIe slot that takes the Synology-listed 10GbE or 25GbE network cards.
Creative AI is a poor fit for the DS1823xs+. GPU expansion and hardware acceleration are both vendor confirmed as unsupported, because the Ryzen V1780B has no integrated GPU or NPU and the PCIe slot is documented for network cards only.
Out of the box the DS1823xs+ has 8GB; 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 DS1823xs+: 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 DS1823xs+ is better as the document store behind a RAG system whose model runs on stronger hardware.
Built-in networking: 10GbE + 2 x 1GbE. Plenty for a shared knowledge base with several users.
| Configuration | RAM | SSD | Notes |
|---|---|---|---|
| DS1823xs+ 8GB ECC | 8GB | None | 8 GB DDR4 ECC SODIMM (1x 8 GB), 2 slots, max 32 GB (16 GB x 2). |
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 46 and Business at 43, 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.
Other AI Capable systems closest in price.
Yes, with a memory upgrade. DeepSeek-R1 32B (Qwen distill) fits at Q4 (Estimated), needing 20GB against the 32GB maximum. It does not fit at Q8 (Estimated), which needs 35GB. The 8GB included would not hold it (Estimated). Inference would be CPU-only through Container Manager, because the DS1823xs+ has no GPU or NPU. This is a memory calculation, not a benchmark.
Yes. The DS1823xs+ uses DDR4 ECC SODIMM, ships with 8GB as a single module, and has 2 slots with a maximum of 32GB. The configuration notes describe that maximum as 16GB x 2. The memory sits in slots rather than being soldered. A larger upgrade is also what lets bigger models load, so it matters most if you plan any local AI.
No. GPU expansion is vendor confirmed as unsupported. The PCIe Gen3 x8 slot (x4 link) is listed by Synology only for 10GbE and 25GbE network cards, no GPU support is documented, and the CPU has no integrated GPU. The system has no OCuLink port, no USB4 and no Thunderbolt, so there is no external GPU route either.
Yes. The DS1823xs+ uses DDR4 ECC SODIMM, and the module in the DS1823xs+ 8GB ECC configuration is ECC. The maximum is 32GB, as 16GB x 2 across the 2 slots, so upgrades should use the same ECC type. Paired with the 5-year warranty, the 10GbE port and Surveillance Station support for up to 75 IP cameras, that makes it a steady business file server, even though AI work stays on the 4-core Ryzen V1780B.
5 years. That is the warranty period Synology lists for the DS1823xs+. The record shows one sold configuration, the DS1823xs+ 8GB ECC, with 8GB of DDR4 ECC SODIMM. The system was released in 2023. Check the warranty terms with Synology or with the seller you buy from.
Yes. Synology lists the DS1823xs+ among the models that apply to Virtual Machine Manager, and Docker is supported through Container Manager. The Ryzen V1780B has 4 cores, and memory starts at 8GB with a 32GB maximum, so virtual machines and containers share that memory. Adding RAM is the practical step before running several at once.
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 10GbE + 2 x 1GbE built in, and the 1x PCIe Gen3 x8 slot (x4 link); Synology-listed NICs: E25G30-F2 (25GbE), E10G30-F2/E10G30-T2/E10G18-T1 (10GbE) can take a faster network card. The fastest port is 10GbE.
Every field records its source. Specifications were last checked on . Spot an error? Send a correction with a manufacturer link.