AINAS
Synology RS2423RP+ 12-bay NAS

Synology RS2423RP+

AI CapableSynologyDiscontinued

Why AI Capable: AMD Ryzen V1780B with no NPU or iGPU, no Synology-documented GPU path (PCIe x8 slot with x4 link, not on the GPU card list) and a 32 GB memory ceiling, so CPU-only small models via Container Manager.

Updated

Can the Synology RS2423RP+ run local AI?

Partly. The Synology RS2423RP+ 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 short answer

The RS2423RP+ suits a business or home lab buyer who wants a 12-bay rackmount NAS running Synology DSM, with Docker and virtual machines both supported. It has an AMD Ryzen V1780B with 4 cores, 8GB of DDR4 ECC memory expandable to 32GB, a 1x 10GbE port and 2x 1GbE ports, and a 350W power supply. Surveillance Station is supported for up to 75 IP cameras, and Synology Photos recognition runs on the CPU. Small models can run in Container Manager on the CPU alone. Estimated: models up to DeepSeek-R1 32B (Qwen distill) fit at Q4. The AINAS Score is 40, which reflects a NAS first and an AI box second.

The main thing that rules it out is the lack of any GPU path. The PCIe Gen3 x8 slot runs at a x4 link and the RS2423RP+ is not on Synology's GPU card list, so unlisted models do not support GPU cards. It also has no NPU and no integrated GPU. Anyone planning fast local LLM work, creative AI or GPU-powered AI search should look for a system with a supported GPU slot or an NPU, plus a memory ceiling above 32GB. Synology has also discontinued the RS2423RP+, which matters to buyers who want a model that is still part of its vendor's current range.

Current offers

No verified price

We have not verified a listing for the Synology RS2423RP+ 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.

Key specifications

CPU
AMD Ryzen V1780B
Source: Manufacturer
Included RAM
8GB DDR4 ECC UDIMM
Source: Manufacturer
Maximum RAM
32GB ECC
Source: Manufacturer
Networking
10GbE + 2 x 1GbE
Source: Manufacturer
PCIe
1x PCIe Gen3 x8 slot (x4 link); Synology-listed cards: E25G30-F2 (25GbE), E10G30-F2/E10G30-T2/E10G18-T1 (10GbE), E10M20-T1 and M2D20 (M.2)
Source: Manufacturer
GPU expansion
None
Source: Official docs
Power supply
350W
Source: Manufacturer
OS
Synology DSM
Source: Manufacturer
Docker
Yes
VM support
Yes
Released
2023
Segment
Rackmount

Can the RS2423RP+ run local LLMs?

Each capability shows how it was confirmed: Verified by AINAS, Vendor confirmed, Community confirmed or Unverified.

CapabilitySupportedEvidenceNote
Local LLMLimitedCommunity confirmedCPU-only Ollama via Container Manager on x86 DSM models. 32 GB memory ceiling, no GPU or NPU. Guide covers the same DSM platform, not this exact unit.
Ollama YesCommunity confirmedNot 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 YesCommunity confirmedGuide documents Open WebUI alongside Ollama on Synology DSM via Container Manager; same DSM platform, not this exact unit.
RAGLimitedUnverifiedNo 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 NoVendor confirmedGPU-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 NoVendor confirmed1x PCIe Gen3 x8 slot (x4 link) exists but this model is not on the Synology GPU card list, which says unlisted models do not support GPU cards.
Hardware acceleration NoVendor confirmedSpec lists a hardware encryption engine only; no integrated GPU, NPU or hardware transcoding listed.
AI photos YesVendor confirmedSynology Photos face and object recognition listed for this model (on-device, CPU).
AI videoLimitedVendor confirmedNo 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 YesVendor confirmedSurveillance Station supported, up to 75 IP cameras (1080p H.264, 2100 FPS); 2 free licences, more require purchase.

What AI models can the RS2423RP+ run?

Calculated from the RS2423RP+'s memory and each model's published size at each quantization. Rows marked Estimated are calculations, not benchmarks. Check any model.

ModelBest quantizationRuns?Memory neededExpected performanceVerification
Llama 3.2 3BLlama, 3.21BQ8Yes13GBNot measuredEstimated
Llama 3.1 8BLlama, 8.03BQ8Yes19GBNot measuredEstimated
Qwen3 8BQwen, 8.19BQ8Yes19GBNot measuredEstimated
Gemma 3 12BGemma, 11.8BQ8Yes24GBNot measuredEstimated
Qwen3 14BQwen, 14.8BQ8Yes28GBNot measuredEstimated
Phi-4 14BPhi, 14.7BQ8Yes28GBNot measuredEstimated
Mistral Small 3 24BMistral, 23.6BQ4Yes25GBNot measuredEstimated
Gemma 3 27BGemma, 27BQ4Yes29GBNot measuredEstimated
Qwen3 30B A3BQwen, 30.5BQ4Yes31GBNot measuredEstimated
Qwen3 32BQwen, 32.8BQ4Yes32GBNot measuredEstimated
DeepSeek-R1 32B (Qwen distill)DeepSeek, 32.8BQ4Yes32GBNot measuredEstimated
Llama 3.3 70BLlama, 70.6BNone fitsNo60GB at Q4Not measuredEstimated
Llama 4 Scout 17Bx16ELlama, 109BNone fitsNo89GB at Q4Not measuredEstimated
Qwen2.5 72BQwen, 72.7BNone fitsNo65GB at Q4Not measuredEstimated
Mistral Large 2 123BMistral, 123BNone fitsNo96GB at Q4Not measuredEstimated

Workload fit

One verdict per workload, from the RS2423RP+'s use-case scores and capability rows. Unknown means we cannot confirm it, not that it probably works.

Local LLMPoor fit

The RS2423RP+ is a poor choice for local LLM work. Support is limited and only community confirmed, covering CPU-only Ollama in Container Manager, with a 32GB memory ceiling and no GPU or NPU.

Private RAGOK

Private RAG is workable but not confirmed here. Synology offers no local RAG on this model, and document chat through Open WebUI in Docker is plausible but unverified on this unit.

AI searchPoor fit

AI search is a poor fit. Vendor documentation says GPU-powered AI Search in Synology Drive is limited to other models, and the RS2423RP+ is not one of them.

AI photosOK

AI photos is an OK fit. Synology lists face and object recognition in Synology Photos for this model, vendor confirmed, and it runs on the CPU rather than a GPU or NPU.

SurveillanceOK

Surveillance is an OK fit. Surveillance Station is vendor confirmed for up to 75 IP cameras, with 2 free licences and more requiring purchase, though deep video analytics on the NAS are not offered.

Home labOK

Home lab use is OK. Container Manager and Virtual Machine Manager are both supported, and the 12 bays, ECC memory and 10GbE port give room for storage-heavy projects.

BusinessOK

Business use is OK. The RS2423RP+ is a rackmount unit with 12 bays, ECC memory, 3 years of warranty and a 350W power supply, running Synology DSM.

Creative AIPoor fit

Creative AI is a poor fit. GPU expansion and hardware acceleration are both vendor confirmed as unsupported, and the system has no integrated GPU or NPU.

How much RAM does the RS2423RP+ support?

Out of the box the RS2423RP+ has 8GB; the official ceiling is 32GB of DDR4 ECC UDIMM 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.

Can you add a GPU to the RS2423RP+?

There is no supported way to add a GPU to the RS2423RP+: no PCIe slot and no OCuLink. Inference runs on the CPU, so keep to small models.

Is the RS2423RP+ suitable for RAG?

For a personal library, yes. A compact embedding model and a small chat model will run, but the RS2423RP+ 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.

Limitations

  • No GPU path. The x8 slot has a x4 link and the RS2423RP+ is not on Synology's GPU card list, so GPU cards are not supported. This is vendor confirmed.
  • No NPU and no integrated GPU, so all AI work runs on the 4-core CPU. Synology's specification includes no hardware transcoding either.
  • Memory tops out at 32GB. Estimated: Llama 3.3 70B does not fit at Q4 or Q8, and 32B models fit only at Q4.
  • There are no built-in M.2 slots. NVMe storage needs an E10M20-T1 or M2D20 card in the single PCIe slot, which is also the only route to 25GbE.
  • Private RAG is unverified on this unit, and local LLM support is limited and community confirmed from a guide covering the same DSM platform, not this exact unit.

Which RS2423RP+ configurations are sold?

ConfigurationRAMSSDNotes
RS2423RP+ 8GB ECC8GBNone

How is the RS2423RP+ different from the DS3622xs+?

The closest Synology model by bay count and AINAS Score. Only the specifications that differ are listed.

  • Processor: AMD Ryzen V1780B on the RS2423RP+, Intel Xeon D-1531 on the DS3622xs+
  • CPU cores: 4 on the RS2423RP+, 6 on the DS3622xs+
  • Memory fitted: 8GB on the RS2423RP+, 16GB on the DS3622xs+
  • Memory ceiling: 32GB on the RS2423RP+, 48GB on the DS3622xs+
  • Networking: 10GbE + 2 x 1GbE on the RS2423RP+, 2 x 10GbE + 2 x 1GbE on the DS3622xs+
  • Power supply: 350W on the RS2423RP+, 550W on the DS3622xs+
  • Status: discontinued on the RS2423RP+, tracked on the DS3622xs+

See the full Synology DS3622xs+ page

Who should buy the RS2423RP+?

Its strongest AINAS profiles are Home Lab at 53 and Business at 51, 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.

What are the alternatives to the RS2423RP+?

Other AI Capable systems closest in overall score.

Common questions

Can the RS2423RP+ run DeepSeek-R1 32B?

Yes, at Q4 only. Estimated: DeepSeek-R1 32B (Qwen distill) needs 20GB at Q4 and 35GB at Q8. The 32GB ceiling covers Q4 but not Q8. It would run on the CPU through Container Manager, as there is no GPU or NPU. Estimated: Llama 3.3 70B does not fit at either level.

Can you upgrade the memory in the RS2423RP+?

Yes. It ships with 8GB of DDR4 ECC UDIMM and the maximum is 32GB. The memory sits in slots rather than being soldered, so it can be expanded. Larger models need more memory, and Estimated: the 32GB ceiling is why 70B-class models do not fit.

Does the RS2423RP+ support ECC memory?

Yes. The RS2423RP+ uses DDR4 ECC UDIMM, and the 8GB it ships with is ECC. Any upgrade should stay within the same memory type, up to the 32GB maximum.

Can the RS2423RP+ take a graphics card?

No. It has a PCIe Gen3 x8 slot with a x4 link, but Synology says unlisted models do not support GPU cards and this model is not on the list. The slot is for the Synology-listed 25GbE, 10GbE and M.2 cards.

Does the RS2423RP+ have M.2 slots?

No. It has 0 built-in M.2 slots. M.2 storage is only possible through an optional PCIe adapter, and the Synology-listed cards are the E10M20-T1 and M2D20. Fitting one uses the single PCIe slot.

Does the RS2423RP+ run Docker and virtual machines?

Yes. The RS2423RP+ runs Synology DSM, and both Docker containers and virtual machines are supported. The 4-core AMD Ryzen V1780B and the 8GB installed suit a handful of containers and a light virtual machine alongside storage, and memory can rise to 32GB of DDR4 ECC UDIMM for heavier use. Small AI models can run in Container Manager on the CPU alone, since the RS2423RP+ has no GPU or NPU.

Can the RS2423RP+ run Ollama?

Yes. Ollama support is confirmed by community reports. See the capability table above for the source.

Does Open WebUI work on the RS2423RP+?

Yes. Open WebUI support is confirmed by community reports. See the capability table above for the source.

Does the RS2423RP+ do AI photo recognition?

Yes. AI photos support is documented by the manufacturer. See the capability table above for the source.

Can the RS2423RP+ run AI surveillance?

Yes. Surveillance AI support is documented by the manufacturer. See the capability table above for the source.

Does the RS2423RP+ have hardware AI acceleration?

No. Hardware acceleration support is documented by the manufacturer. See the capability table above for the source.

How fast is the RS2423RP+'s network?

It has 10GbE + 2 x 1GbE built in, and the 1x PCIe Gen3 x8 slot (x4 link); Synology-listed cards: E25G30-F2 (25GbE), E10G30-F2/E10G30-T2/E10G18-T1 (10GbE), E10M20-T1 and M2D20 (M.2) can take a faster network card. The fastest port is 10GbE.

Where do these specifications come from?

Every field records its source. Specifications were last checked on . Spot an error? Send a correction with a manufacturer link.