16GB max RAM · 6 bays · 2 x 2.5GbE
AINAS Score 31
No verified price

AI CapableSynology
Why AI Capable: AMD Ryzen V1500B with no NPU and no iGPU, 32 GB maximum memory, and a PCIe Gen3 x8 (x4 link) slot that Synology supports only for NICs and M.2 adapters, so CPU-only small models via Container Manager.
Updated
Can the Synology DS2422+ run local AI?
Only lightly. Expect models up to the 14B class, with 32B class models a tight fit (Estimated) on the Synology DS2422+: AMD Ryzen V1500B does the work with up to 32GB 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 DS2422+ is a 12-bay Synology NAS for people who want storage first and light AI as a side job. It has 12 bays, 4 x 1GbE, a 550W power supply and DDR4 ECC SODIMM memory that takes up to 32GB. It runs Synology DSM with Docker and virtual machines. Synology Photos facial and object recognition is vendor confirmed, and Surveillance Station handles up to 40 IP cameras. The AINAS Score is 31, which reflects a CPU-only AI path. The AMD Ryzen V1500B has no NPU and no integrated GPU, so any model runs on the CPU through Container Manager. Community guides recommend small 1B to 3B models.
The main limit is the lack of a GPU path. The PCIe Gen3 x8 slot (x4 link) is supported by Synology only for 10GbE and 25GbE network cards and M.2 adapters, and no GPU support is documented. Anyone planning to run larger local models at usable speed, or to use Synology AI Search, should look elsewhere. They need a NAS with a GPU expansion path, an integrated GPU or an NPU, plus a memory ceiling well above 32GB. The 4GB of included memory also needs upgrading before running Ollama. Buyers who only need storage, photo recognition and cameras are the right audience.
Amazon UK
DS2422+ 4GB ECC
No current price
Checked , no price yet
Out of stock
Buy on AmazonAmazon US
DS2422+ 4GB ECC
Ships from the US; delivery and import charges shown at checkout
$2,114.99
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; guide uses a V1500B DS925+ and recommends small (1B to 3B) models. Needs RAM upgrade beyond 4 GB. |
| 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. |
| RAG | Limited | Unverified | No Synology local RAG on this model; AI Console bridges to cloud or OpenAI-compatible APIs. Open WebUI document chat via Docker plausible but not verified on this unit. |
| AI search | No | Vendor confirmed | Synology AI Search in Drive needs GPU-powered models, available only on supported systems with a GPU (AI Console 2.0 beta lists FS3420, FS6420, RS11626xs+, RS3626xs, RS4826xs+, RS6426xs+); this model is not listed. |
| GPU expansion | No | Vendor confirmed | PCIe Gen3 x8 (x4 link) slot exists but Synology lists only 10/25GbE NICs and M.2 adapter cards; no GPU support documented. |
| Hardware acceleration | No | Community confirmed | Ryzen V1500B has no integrated GPU and no NPU; no hardware transcoding or AI acceleration. |
| AI photos | Yes | Vendor confirmed | Synology Photos facial and object recognition listed (on-device, CPU). |
| AI video | Limited | Community confirmed | No on-NAS deep video analytics; Surveillance Station can use on-camera AI from Synology BC500/TC500 cameras. |
| Surveillance AI | Yes | Vendor confirmed | Surveillance Station up to 40 IP cameras (1080p H.264); 2 free licences. |
Calculated from the DS2422+'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 DS2422+'s use-case scores and capability rows. Unknown means we cannot confirm it, not that it probably works.
The DS2422+ is a poor choice for running local language models. Support is limited and community confirmed only: CPU-only Ollama runs in Container Manager, guides suggest 1B to 3B models, and the included 4GB of memory needs upgrading.
Private RAG is a poor fit on the DS2422+. Synology offers no local RAG on this model, and document chat through Open WebUI in Docker is plausible but Unverified, so it is unconfirmed here.
AI search is a poor fit, and Synology confirms it does not work here. Synology AI Search in Drive needs GPU-powered models on supported systems, and the DS2422+ is not on the list.
The verdict for AI photos is poor, even though the feature is listed. Synology Photos facial and object recognition is vendor confirmed, but it runs on the CPU because the DS2422+ has no NPU or integrated GPU.
Surveillance is rated poor for AI work on the DS2422+. Surveillance Station supports up to 40 IP cameras with 2 free licences, but there is no on-NAS deep video analytics, only on-camera AI.
Home lab use is rated poor despite some useful platform features. Docker and virtual machines are both supported, and memory goes to 32GB, but there is no GPU path and no onboard M.2 slot.
Business use is rated poor on the AI side. The DS2422+ offers ECC memory, 12 bays and a 3-year warranty, but its networking is 4 x 1GbE and it has no GPU or NPU for AI work.
Creative AI is a poor fit because there is no acceleration. GPU expansion is vendor confirmed as unsupported, hardware acceleration is absent, and local language model support is limited to CPU-only use.
Plan on upgrading. 4GB is fitted as standard, while the DS2422+ accepts 32GB of DDR4 ECC SODIMM, ECC included, which is the difference between only very small models of around 1B to 3B parameters and models up to the 14B class, with 32B class models a tight fit (Estimated).
Our estimate for the biggest model that fits in 32GB is about 40B parameters at 4-bit, after setting aside 8GB for the system. Long context windows reduce that figure (Estimated).
ECC memory support is a plus for always-on systems that also hold important files.
A graphics card is not an option on the DS2422+, 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 DS2422+, while the answering model needs more compute than it has.
For network access it has 4 x 1GbE. Enough for light use; large imports will take a while.
| Configuration | RAM | SSD | Notes |
|---|---|---|---|
| DS2422+ 4GB ECC | 4GB | None | 4 GB DDR4 ECC SODIMM (1x 4 GB), 2 slots, max 32 GB. |
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 DS2422+ scores highest (Home Lab 39/100), followed by Business (35/100).
Less suited to buyers who expect to add a graphics card later and teams moving large files over the network every day.
Other AI Capable systems closest in price.
Yes, on paper. DeepSeek-R1 32B (Qwen distill) is the largest model listed on this page that fits at Q4 (Estimated), needing 20GB, so it needs a memory upgrade from the included 4GB. It does not fit at Q8 (Estimated). This is a calculation, not a benchmark. It would run on the CPU only, and community guides recommend 1B to 3B models for this class of setup.
No. Synology confirms GPU expansion is not supported. The PCIe Gen3 x8 slot (x4 link) is listed only for 10GbE and 25GbE network cards and M.2 adapters. The Ryzen V1500B has no integrated GPU, so there is no hardware acceleration or transcoding.
Yes. The DS2422+ has 2 slots and takes up to 32GB (16GB x 2) of DDR4 ECC SODIMM. It ships with one 4GB module. Community guidance says Ollama needs a memory upgrade beyond the included 4GB.
No. There are 0 onboard M.2 slots. NVMe cache needs an M2D20 or E10M20-T1 adapter card in the single PCIe slot. That slot then cannot also hold a 10GbE or 25GbE network card.
Yes. The DS2422+ uses DDR4 ECC SODIMM, and the DS2422+ 4GB ECC configuration comes with one 4GB ECC module. The second slot takes another module, up to 32GB as 16GB x 2. ECC suits a 12-bay system holding large amounts of data, and the 550W power supply and 3-year warranty point the same way: this is a storage server first, with CPU-only AI on the 4-core Ryzen V1500B as a side job.
Yes. The DS2422+ runs Docker through Container Manager on Synology DSM, and it also supports virtual machines. Ollama is not in Package Center, but the ollama/ollama container runs on the CPU, as confirmed by the community. Open WebUI containers are also documented.
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 4 x 1GbE built in, and the 1x PCIe Gen3 x8 slot (x4 link); Synology-listed cards: E10G30-F2/E10G30-T2/E10G18-T1 (10GbE), E25G30-F2 (25GbE), E10M20-T1, M2D20 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.