32GB max RAM · 2 bays · 2 x 2.5GbE
AINAS Score 29
No verified price

AI CapableSynologyDiscontinued
Why AI Capable: AMD Ryzen R1600 (2C/4T) with no NPU or iGPU, 32 GB max DDR4 ECC, and only a PCIe Gen3 x2 network upgrade slot (E10G22-T1-Mini), so no GPU path; CPU-only small models via Container Manager.
Updated
Can the Synology DS1522+ run local AI?
The Synology DS1522+ can run small local models, with limits. Its AMD Ryzen R1600 and 32GB memory ceiling suit models up to the 14B class, with 32B class models a tight fit (Estimated), so treat it as a storage-first NAS that can host light AI tools.
There is no way to add a discrete GPU, so all inference runs on the CPU.
Local LLM support is confirmed by community reports.
The DS1522+ suits a buyer who wants a five-bay Synology NAS for files, photos and camera recording, with small AI jobs as a side task. It has 5 bays, 2 M.2 slots, 8GB of DDR4 ECC SODIMM expandable to 32GB, and four 1GbE ports. Synology Photos face and object recognition is vendor confirmed on this model, and Surveillance Station is vendor confirmed for up to 40 IP cameras. Docker and virtual machines are both supported on Synology DSM. The AINAS Score is 29, which reflects a CPU-only AI path. Community guides cover CPU-only Ollama in Container Manager, but small quantised models are the realistic target.
The DS1522+ has no GPU path, and that rules it out for anyone who wants to run local models at a usable pace or do creative AI work. Its only expansion slot is a PCIe Gen3 x2 network upgrade slot that takes the E10G22-T1-Mini 10GbE module only. There is no OCuLink, no USB4 and no NPU. Synology has also discontinued it. Buyers who need local AI should look for a system with an integrated GPU or NPU, or a PCIe slot that can take a graphics card, plus more memory headroom than 32GB and a current model rather than a discontinued one.
No verified price
We have not verified a listing for the Synology DS1522+ 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; 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 | Only a PCIe Gen3 x2 network upgrade slot for the E10G22-T1-Mini 10GbE module; no slot usable for a GPU, no OCuLink or USB4. |
| Hardware acceleration | No | Vendor confirmed | Ryzen R1600 has no integrated GPU (AMD lists it without Radeon graphics) and no NPU; no hardware transcoding or AI acceleration. |
| 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 40 IP cameras (1080p H.264, 1050 FPS); 2 free licences, more require purchase. |
Calculated from the DS1522+'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 DS1522+'s use-case scores and capability rows. Unknown means we cannot confirm it, not that it probably works.
The DS1522+ is a poor choice for local LLM work. Ollama runs CPU-only in Container Manager (community confirmed), the local LLM row is only limited, and small quantised models are the realistic target without a GPU or NPU.
Private RAG is a poor fit on the DS1522+. 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, because the DS1522+ does not get it. Synology's GPU-powered AI Search for Drive in the AI Console 2.0 beta is limited to other models, and the capability row says no (vendor confirmed).
The verdict for AI photos is poor in our scoring, even though the feature itself works. Synology Photos face and object recognition is vendor confirmed on this model, but it runs on the CPU only, with no GPU or NPU.
Surveillance is rated poor overall for the DS1522+, despite basic support. Surveillance Station is vendor confirmed for up to 40 IP cameras with 2 free licences, but there is no on-NAS deep video analytics and no hardware acceleration.
Home lab use is rated poor on the DS1522+. It runs Docker and virtual machines under DSM, but a 2-core Ryzen R1600, 32GB maximum memory and 1GbE ports leave little room to grow.
Business use is rated poor for the DS1522+. It has ECC memory and a 3 year warranty, but it is discontinued, which complicates long-term planning, and its networking is four 1GbE ports.
Creative AI is a poor fit for the DS1522+. GPU expansion is vendor confirmed as unsupported, hardware acceleration is not supported, and the only PCIe slot takes a 10GbE network module.
The DS1522+ ships with 8GB of DDR4 ECC SODIMM and supports up to 32GB with ECC. Upgrading to the maximum lifts the model ceiling from small models up to around 7B parameters to models up to the 14B class, with 32B class models a tight fit (both Estimated).
As a rule of thumb, a 4-bit model needs about 0.6GB per billion parameters plus room for context. After leaving around 8GB for the NAS operating system, 32GB leaves space for a model of roughly 40B parameters at most (Estimated).
ECC memory support is a plus for always-on systems that also hold important files.
No. The DS1522+ has no PCIe slot or OCuLink port for a graphics card. Inference runs on the CPU, so keep to small models.
With limits. The DS1522+ can host a small RAG stack such as AnythingLLM or Open WebUI with a compact embedding model, but memory and compute restrict how large the answering model can be. It suits a personal document library more than a team knowledge base.
Networking is 4 x 1GbE. Fine for one or two users; indexing a large archive over the network will be slower.
| Configuration | RAM | SSD | Notes |
|---|---|---|---|
| DS1522+ 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.
The DS1522+ scores best for Home Lab (33/100) and Business (33/100). It suits home lab owners who want one box for storage, containers, media and a few AI services.
It is a weaker fit for buyers who expect to add a graphics card later and for teams moving large files over the network every day.
Other AI Capable systems closest in overall score.
Yes, on memory alone. DeepSeek-R1 32B (Qwen distill) fits at Q4 with 32GB installed (Estimated), but not at Q8 (Estimated). That is a memory calculation, not a benchmark. It would run CPU-only through Container Manager, with no GPU or NPU. Community guides confirm Ollama on this DSM platform, though not on this exact unit. Llama 3.3 70B does not fit at Q4 (Estimated).
32GB is the maximum. The DS1522+ ships with 8GB of DDR4 ECC SODIMM as a single module and has 2 memory slots. The listed upgrade path is 16GB in each slot. Memory sits in slots rather than being soldered. Community notes say 7B class models need more than the base amount.
Yes. The DS1522+ uses DDR4 ECC SODIMM, and the 8GB module it ships with is ECC. The memory is expandable up to 32GB across 2 slots. ECC helps protect stored data from memory errors, which matters for a file server running around the clock.
No. GPU expansion is vendor confirmed as unsupported. The only PCIe slot is a Gen3 x2 network upgrade slot for the E10G22-T1-Mini 10GbE module, and no other module fits. There is no OCuLink, USB4 or Thunderbolt port to connect an external GPU either.
Yes, two. The DS1522+ has 2 NVMe slots beside its 5 drive bays, so fast flash does not cost a bay. They do not open a GPU path: the only PCIe slot is a Gen3 x2 network upgrade slot for the E10G22-T1-Mini 10GbE module, and there is no OCuLink, USB4 or Thunderbolt. The 2-core Ryzen R1600 has no integrated GPU or NPU either, so AI work on this system stays on the CPU, with up to 32GB of DDR4 ECC memory.
Yes. The DS1522+ is on Synology's Container Manager supported models list, so Docker containers run under DSM. It is also on the Virtual Machine Manager list, so virtual machines are supported. Containers use the 2-core Ryzen R1600 CPU only, since there is no GPU or NPU.
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 4 x 1GbE built in, and the 1x PCIe Gen3 x2 network upgrade slot (E10G22-T1-Mini 10GbE RJ-45 module only) 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.