64GB max RAM · 8 bays · 2 x 2.5GbE
AINAS Score 49
£1,320
Amazon UK · Verified
AI CapableiXsystemsDiscontinued
Why AI Capable: CPU model unpublished (6 to 10 cores, ServeTheHome infers Xeon), PCIe slots with no published width, and a 96GB memory ceiling, so the x8 GPU expansion the AI Ready line needs under 128GB is not shown.
Updated
Can the iXsystems TrueNAS R10 run local AI?
Only lightly. Expect 70B class models at 4-bit with room left for longer context (Estimated) on the iXsystems TrueNAS R10: Intel Xeon inferred, model not published (6 to 10 cores) does the work with up to 96GB 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 not yet verified.
The TrueNAS R10 suits storage-first buyers who want a rackmount TrueNAS system with a bit of container-based AI on the side. It has 16 bays, 2 x 10GbE, 32GB of memory as the starting configuration and up to 96GB. Docker and virtual machines are both listed. The TrueNAS Apps catalog lists Ollama, Open WebUI, Immich and Frigate, all as community apps with limited support. Memory-based fit estimates are generous: Mistral Large 2 123B fits at Q4 (Estimated). It is a CPU-only system with 10 cores at most, so treat it as a file server that can also host small AI services. The AINAS Score is 50.
The main thing that rules it out is the lack of a documented GPU path. The R10 has PCIe expansion slots, but their count and width are not published, and iXsystems does not document GPU use. There is no NPU and no integrated GPU either. Anyone planning creative AI, heavy inference or hardware-accelerated detection should look for a system with a documented x8 or wider PCIe slot for a graphics card, or an NPU with a stated TOPS figure. iXsystems has also discontinued the R10, with support due to end on 2030-01-31.
No verified price
We have not verified a listing for the iXsystems TrueNAS R10 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 | Unverified | Docker apps on a CPU of 6 to 10 cores with 96GB maximum; Ollama app exists in the TrueNAS catalog but no vendor statement of LLM use on this model. Enterprise licensed systems need apps enabled in the licence. |
| Ollama | Limited | Vendor confirmed | Ollama listed in the TrueNAS Apps catalog (community train, TrueNAS 24.10.2.2 or newer). Community support only. |
| Open WebUI | Limited | Vendor confirmed | Open WebUI listed in the TrueNAS Apps catalog (community train). Community support only. |
| RAG | Limited | Unverified | Possible via Open WebUI; no vendor or platform-specific evidence found. |
| AI search | No | Unverified | No AI or semantic search feature documented on the R-Series page. |
| GPU expansion | Limited | Unverified | PCIe expansion exists; GPU use is not documented by iXsystems. |
| Hardware acceleration | No | Unverified | No GPU, NPU or accelerator listed in R-Series specifications. |
| AI photos | Limited | Vendor confirmed | Immich listed in the TrueNAS Apps catalog (community train). |
| AI video | No | Unverified | No AI video feature documented. |
| Surveillance AI | Limited | Vendor confirmed | Frigate NVR listed in the TrueNAS Apps catalog (community train). No detection accelerator listed. |
Calculated from the TrueNAS R10'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 | Q5 | Yes | 68GB | Not measured | Estimated |
| Llama 4 Scout 17Bx16ELlama, 109B | Q4 | Yes | 89GB | Not measured | Estimated |
| Qwen2.5 72BQwen, 72.7B | Q5 | Yes | 73GB | Not measured | Estimated |
| Mistral Large 2 123BMistral, 123B | Q4 | Yes | 96GB | Not measured | Estimated |
One verdict per workload, from the TrueNAS R10's use-case scores and capability rows. Unknown means we cannot confirm it, not that it probably works.
The R10 is an acceptable local LLM host, with caveats. Ollama is vendor confirmed as a limited, community-supported app, but local LLM use on this model is unconfirmed, and the system has no GPU or NPU.
Private RAG is workable on the R10, though not proven. The Open WebUI app is vendor confirmed as limited community support, while RAG itself is unverified and only described as possible through that app on up to 96GB of memory.
AI search is a poor fit for the R10. The R-Series page documents no AI or semantic search feature, and that capability is marked as not supported and unverified.
AI photos are acceptable on the R10. Immich is listed in the TrueNAS Apps catalog and vendor confirmed, with limited community support, and Docker is available when enabled in the licence.
Surveillance is acceptable on the R10. Frigate NVR is listed in the TrueNAS Apps catalog (vendor confirmed, limited, community train), but no detection accelerator is listed, so detection would run on the CPU.
The R10 is a good home lab system. It lists Docker and virtual machine support, TrueNAS as the operating system, 16 bays and 2 x 10GbE, though VM licensing is not confirmed.
The R10 is a good business storage system. It offers 16 bays, redundant power supplies, 2 x 10GbE and TrueNAS Enterprise, with support running to 2030-01-31 even though iXsystems has discontinued it.
We cannot confirm the R10 for creative AI. PCIe expansion exists, but GPU use is unverified and undocumented by iXsystems, and hardware acceleration is listed as not supported.
Plan on upgrading. 32GB is fitted as standard, while the TrueNAS R10 accepts 96GB of memory, which is the difference between models up to the 14B class, with 32B class models a tight fit and 70B class models at 4-bit with room left for longer context (Estimated).
Our estimate for the biggest model that fits in 96GB is about 146B parameters at 4-bit, after setting aside 8GB for the system. Long context windows reduce that figure (Estimated).
A graphics card is not an option on the TrueNAS R10, 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 TrueNAS R10, while the answering model needs more compute than it has.
For network access it has 2 x 10GbE. Fast enough that the network will not be the bottleneck.
| Configuration | RAM | SSD | Notes |
|---|---|---|---|
| 32GB to 96GB, quote configured | 96GB | None |
The closest iXsystems 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 TrueNAS R10 scores highest (Home Lab 64/100), followed by Business (62/100).
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 Capable systems closest in overall score.
Workloads it suits
Yes on memory alone, at Q4 only (Estimated). It needs 73GB at Q4 and the R10 takes up to 96GB. Q8 needs 130GB, which does not fit (Estimated). This is a calculation, not a benchmark, and there is no GPU or NPU to help.
Up to 96GB. The lowest configuration has 32GB, and the range is 32GB to 96GB per controller. Memory is listed as expandable. The memory type and ECC support are not published, so check with iXsystems before assuming either.
Unconfirmed. The R10 has PCIe expansion slots, but their count and width are not published, and iXsystems does not document GPU use. GPU expansion is marked limited and unverified, and hardware acceleration is listed as not supported.
No. iXsystems lists no M.2 or NVMe slots for the R10, so all storage goes through its 16 bays. Networking is 2 x 10GbE, and the PCIe expansion slots have no published count or width, so adding NVMe through a card is not documented either. The R10 is built around its drive bays, which means model files and app data share the same storage pool as everything else on the system.
Yes. Docker is listed, through the TrueNAS Apps catalog. Apps on Enterprise licensed systems must be enabled in the licence. Ollama, Open WebUI, Immich and Frigate are all in the catalog as community apps with limited support.
No. Estimated: Qwen3 235B A22B is 142GB at Q4 and 250GB at Q8, and the R10 tops out at 96GB, so it does not fit at either level. Mistral Large 2 123B at Q4 is the largest listed model that fits (Estimated), and Llama 3.3 70B fits at Q4 as well (Estimated). These are memory calculations, not benchmarks, and with no GPU or NPU, inference would run on a CPU of 6 to 10 cores.
Partly. Ollama support is documented by the manufacturer. See the capability table above for the source.
Partly. Open WebUI support is documented by the manufacturer. See the capability table above for the source.
Partly. AI photos support is documented by the manufacturer. See the capability table above for the source.
Partly. Surveillance AI support is documented by the manufacturer. See the capability table above for the source.
No. Hardware acceleration support is not yet verified. See the capability table above for the source.
It has 2 x 10GbE built in, and the PCIe expansion slots; count and width not published 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.