64GB max RAM · 8 bays · 2.5GbE
AINAS Score 58
No verified price

AI ReadySynologyDiscontinued
Why AI Ready: Intel Xeon D-1541 with no iGPU or NPU, two PCIe Gen3 x8 slots but no Synology-documented GPU support, and a 128 GB memory ceiling, so ready rather than native.
Updated
Can the Synology FS3410 run local AI?
Only lightly. Expect 70B class models at higher-quality quantization, or large mixture-of-experts models at 4-bit (Estimated) on the Synology FS3410: Intel Xeon D-1541 does the work with up to 128GB 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 FS3410 suits buyers who want a 24-bay all-flash rackmount NAS for business storage, surveillance and a home lab, with some CPU-only AI as an extra. It has an Intel Xeon D-1541 with 8 cores, 16GB of DDR4 ECC RDIMM memory that expands to 128GB, 2x 10GbE and 4x 1GbE ports, and two PCIe Gen3 x8 slots. Docker and virtual machines are both supported. Surveillance Station covers up to 160 IP cameras. It carries a 5 year warranty and a 550W power supply. Models up to Mistral Large 2 123B load at Q4 with the full 128GB (Estimated), though that is a memory calculation and not a benchmark. The AINAS Score is 57.
The FS3410 is discontinued, with Synology giving its status as Phase Out, and that rules it out for anyone who wants years of vendor support for a business system. Buyers who want GPU-accelerated AI are also affected, because Synology does not support GPU cards in this model and there is no NPU. Both PCIe Gen3 x8 slots are for network cards, such as the E25G30-F2 for 25GbE and the listed 10GbE cards. If you need faster local AI, look for a current model with a documented GPU card path or an NPU, a PCIe slot on the vendor's supported card list, and at least 128GB of memory. The 16GB fitted also needs raising before the larger Estimated fits apply.
No verified price
We have not verified a listing for the Synology FS3410 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 | The FS3410 can only run Ollama on its CPU through Container Manager, as other x86 DSM models do. Its ceiling is 128 GB with no GPU or NPU, and Synology's guide covers DSM generally rather than this flash unit. |
| Ollama | Yes | Community confirmed | Package Center has no Ollama for the FS3410. The ollama/ollama container runs in Container Manager, CPU only, and the guide covers DSM generally rather than this flash unit. |
| Open WebUI | Yes | Community confirmed | Synology's guide pairs Open WebUI with Ollama in Container Manager on DSM generally; it does not test the FS3410 itself. |
| RAG | Limited | Unverified | The FS3410 has no Synology local RAG. AI Console bridges to third-party providers, and Open WebUI document chat via Docker is plausible but unverified on this flash unit. |
| AI search | No | Vendor confirmed | Not on the FS3410: GPU-powered AI Search in Synology Drive is limited, per the AI Console 2.0 and AI Runtime 1.0 betas, to the FS3420, FS6420 and 26-series rack models. |
| GPU expansion | No | Vendor confirmed | The FS3410 has 2x PCIe Gen3 x8 slots (x8 link) but is missing from Synology's GPU card list, and Synology says unlisted models do not support GPU cards. |
| Hardware acceleration | No | Vendor confirmed | For the FS3410, Synology lists a hardware encryption engine only: no integrated GPU, NPU or hardware transcoding. |
| AI photos | No | Vendor confirmed | Synology Photos does not list the FS3410, so it has no face or object recognition. |
| AI video | Limited | Vendor confirmed | No 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 | Yes | Vendor confirmed | Surveillance Station supported, up to 160 IP cameras (1080p H.264, 2800 FPS); 2 free licences, more require purchase. |
Calculated from the FS3410'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 | Q8 | Yes | 38GB | Not measured | Estimated |
| Gemma 3 27BGemma, 27B | Q8 | Yes | 44GB | Not measured | Estimated |
| Qwen3 30B A3BQwen, 30.5B | Q8 | Yes | 47GB | Not measured | Estimated |
| Qwen3 32BQwen, 32.8B | Q8 | Yes | 50GB | Not measured | Estimated |
| DeepSeek-R1 32B (Qwen distill)DeepSeek, 32.8B | Q8 | Yes | 50GB | Not measured | Estimated |
| Llama 3.3 70BLlama, 70.6B | Q8 | Yes | 98GB | Not measured | Estimated |
| Llama 4 Scout 17Bx16ELlama, 109B | Q4 | Yes | 89GB | Not measured | Estimated |
| Qwen2.5 72BQwen, 72.7B | Q8 | Yes | 101GB | Not measured | Estimated |
| Mistral Large 2 123BMistral, 123B | Q5 | Yes | 112GB | Not measured | Estimated |
One verdict per workload, from the FS3410's use-case scores and capability rows. Unknown means we cannot confirm it, not that it probably works.
The FS3410 is an acceptable local LLM host, with limits. Support is limited and community confirmed only, running Ollama on the CPU through Container Manager with no GPU or NPU, and memory expands to 128GB.
Private RAG is workable but not turnkey on the FS3410. The RAG row is limited and Unverified: Synology offers no local RAG, and Open WebUI document chat through Docker is plausible but unconfirmed on this unit.
AI search is a poor fit for the FS3410. Synology confirms that GPU-powered AI Search in Synology Drive is not supported on this model, as it is reserved for other rack models.
The FS3410 is poor for AI photos. Synology Photos does not list this model, so Synology confirms there is no face or object recognition.
Surveillance is a strong use for the FS3410. Surveillance Station is vendor confirmed for up to 160 IP cameras, with 2 free licences, though extra licences must be bought and on-NAS video analytics are not offered.
The FS3410 is a good home lab machine. It supports Docker and virtual machines, and offers 8 cores, ECC memory up to 128GB, 2x 10GbE and two PCIe Gen3 x8 slots.
The FS3410 is a good business storage choice. It has 24 bays, ECC RDIMM memory, a 5 year warranty and 2x 10GbE, with a 25GbE card on Synology's listed cards for the PCIe slots.
Creative AI is only acceptable on the FS3410. Synology confirms there is no GPU expansion and no hardware acceleration, so work depends on the CPU and memory, with local LLM support limited.
Plan on upgrading. 16GB is fitted as standard, while the FS3410 accepts 128GB of DDR4 ECC RDIMM, ECC included, which is the difference between 7B to 8B class models and 70B class models at higher-quality quantization, or large mixture-of-experts models at 4-bit (Estimated).
Our estimate for the biggest model that fits in 128GB is about 200B parameters at 4-bit, after setting aside 8GB for the system. Long context windows reduce that figure (Estimated).
ECC support protects against silent memory errors on a box that runs around the clock.
A graphics card is not an option on the FS3410, 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 FS3410, while the answering model needs more compute than it has.
For network access it has 2 x 10GbE + 4 x 1GbE. Fast enough that the network will not be the bottleneck.
| Configuration | RAM | SSD | Notes |
|---|---|---|---|
| FS3410 16GB ECC | 16GB | None |
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 FS3410 scores highest (Home Lab 69/100), followed by Business (67/100).
Less suited to buyers who expect to add a graphics card later and buyers who want a model with a long support life ahead.
Other AI Ready systems closest in overall score.
64GB max RAM · 8 bays · 2.5GbE
AINAS Score 58
No verified price
1024GB max RAM · 10 bays · 25GbE
AINAS Score 56
$13,999.00
Amazon US · Verified
Ships from the US; delivery and import charges shown at checkout
64GB max RAM · 4 bays · 2 x 2.5GbE
AINAS Score 56
Price awaiting re-verification
Last checked
Workloads it suits
Yes at Q4, but only as an estimate. Mistral Large 2 123B needs 73GB at Q4 and fits with the 128GB maximum (Estimated). At Q8 it needs 130GB and does not fit (Estimated). It would run on the CPU only, through Ollama in Container Manager, which is community confirmed. Qwen3 235B A22B does not fit at Q4 (Estimated).
128GB is the maximum. The FS3410 ships with 16GB of DDR4 ECC RDIMM and the memory is expandable. It uses registered ECC modules, so check that any upgrade matches that type. Memory is the main limit on model size, since there is no GPU or NPU to share the load.
No. It has two PCIe Gen3 x8 slots with an x8 link, but Synology's GPU card list does not include the FS3410. Synology says unlisted models do not support GPU cards. The slots suit the listed network cards, including a 25GbE card and several 10GbE cards.
Yes. Container Manager runs Docker on Synology DSM, and virtual machines are supported too. Package Center has no Ollama for the FS3410, but the ollama/ollama container runs on the CPU only in Container Manager, which is community confirmed. Synology's guide pairs Open WebUI with it on DSM generally rather than on this flash unit. The 8-core Xeon D-1541 and up to 128GB of DDR4 ECC RDIMM give room for several containers and virtual machines beside a CPU-only model.
5 years. Synology's specification gives the FS3410 a 5 year warranty. Synology has discontinued it, with its status given as Phase Out, so check how the remaining cover applies to the unit you buy. The system was released in 2022 and has a 550W power supply, 24 all-flash bays, 2x 10GbE and 4x 1GbE ports. Surveillance Station covers up to 160 IP cameras, with 2 free licences and more for purchase.
Yes. It uses DDR4 ECC RDIMM memory, with 16GB included and a 128GB maximum. ECC suits storage and business work, where memory errors matter. Any upgrade modules need to be the same ECC RDIMM type.
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.
No. 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 2 x 10GbE + 4 x 1GbE built in, and the 2x PCIe Gen3 x8 slots (x8 link); Synology-listed cards: E25G30-F2 (25GbE), E10G30-F2/E10G30-T2/E10G18-T1 (10GbE) can take a faster network card. The fastest port is 2 x 10GbE.
Every field records its source. Specifications were last checked on . Spot an error? Send a correction with a manufacturer link.