64GB max RAM · 10 bays · 2 x 10GbE
AINAS Score 43
£1,699
Amazon UK · Verified

AI CapableiXsystems
Why AI Capable: Intel Atom C3758 8-core with no NPU and no integrated GPU, a PCIe 3.0 x4 slot iXsystems only documents for NICs, and 64GB ECC DDR4 maximum, so it runs Docker apps and small CPU models only.
Updated
Can the iXsystems TrueNAS Mini X+ run local AI?
Partly. The iXsystems TrueNAS Mini X+ runs local models on Intel Atom C3758 alone, and its 64GB ceiling allows 32B class models comfortably, and 70B class models at 4-bit with little headroom (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 not yet verified.
The TrueNAS Mini X+ suits a buyer who wants a storage-first NAS that can also run a few container apps. It has 7 bays (5 x 3.5in and 2 x 2.5in SSD), 32GB of DDR4 ECC memory expandable to 64GB, and 2 x 10GbE. It runs TrueNAS with Docker and virtual machines. Open WebUI is vendor confirmed in the TrueNAS Apps catalog. Ollama is listed there too, but support is limited and would be CPU-only on the 8-core Intel Atom C3758. The AINAS Score is 43. Llama 3.3 70B is the largest model listed that fits at Q4 (Estimated), and that estimate is a calculation, not a benchmark.
The main limit is the lack of any GPU path. The Mini X+ has no integrated GPU and no NPU. Its PCIe 3.0 x4 slot is documented by iXsystems only for a 10G NIC, and GPU use is unconfirmed. Anyone planning fast local inference, image generation or hardware-accelerated detection should look elsewhere. Look for a system with a discrete GPU slot that the maker documents for graphics cards, or a dedicated NPU with a stated TOPS figure, or OCuLink or Thunderbolt for an external GPU. Memory that loads a model is not the same as hardware that runs it quickly.
No verified price
We have not verified a listing for the iXsystems TrueNAS Mini X+ 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 | CPU-only on an 8-core Atom C3758 with no GPU or NPU; Ollama app exists in the TrueNAS catalog but no vendor statement on LLM use for the Mini. |
| Ollama | Limited | Vendor confirmed | Ollama listed in the TrueNAS Apps catalog (community train). Would run CPU-only on this hardware. |
| Open WebUI | Yes | Vendor confirmed | Open WebUI listed in the TrueNAS Apps catalog (community train). |
| RAG | Limited | Unverified | Possible via Open WebUI document features; no vendor or platform-specific evidence found. |
| AI search | No | Unverified | No AI or semantic search feature documented for TrueNAS on the Mini. |
| GPU expansion | Limited | Unverified | PCIe 3.0 x4 slot in a compact chassis; iXsystems documents it only for a 10G NIC. GPU use not documented. |
| Hardware acceleration | No | Vendor confirmed | Atom C3758 has no integrated GPU; only hardware-accelerated disk encryption is listed. |
| AI photos | Limited | Vendor confirmed | Immich listed in the TrueNAS Apps catalog (community train); ML runs on CPU only. |
| AI video | No | Unverified | No AI video feature documented. |
| Surveillance AI | Limited | Vendor confirmed | Frigate listed in the TrueNAS Apps catalog (community train); vendor page also lists video surveillance as a use case. No GPU or AI accelerator for detection. |
Calculated from the TrueNAS Mini X+'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 | Q4 | Yes | 60GB | Not measured | Estimated |
| Llama 4 Scout 17Bx16ELlama, 109B | None fits | No | 89GB at Q4 | Not measured | Estimated |
| Qwen2.5 72BQwen, 72.7B | Q3 | Yes | 54GB | Not measured | Estimated |
| Mistral Large 2 123BMistral, 123B | Q2 | Yes | 62GB | Not measured | Estimated |
One verdict per workload, from the TrueNAS Mini X+'s use-case scores and capability rows. Unknown means we cannot confirm it, not that it probably works.
The Mini X+ is an acceptable local LLM host, with caveats. Ollama is vendor confirmed but limited and CPU-only, and the local LLM row is Unverified, so there is no vendor statement on LLM use for this model.
Private RAG is workable here. Open WebUI is vendor confirmed in the TrueNAS Apps catalog, but the RAG row is limited and Unverified, resting on Open WebUI document features with no platform-specific evidence.
AI search is a poor fit for the Mini X+. No AI or semantic search feature is documented for TrueNAS on this system, and that row is marked no and Unverified.
AI photos are acceptable on the Mini X+. Immich is vendor confirmed in the TrueNAS Apps catalog, though support is limited because its machine learning runs on the CPU only.
Surveillance is an acceptable use for the Mini X+. Frigate is vendor confirmed in the Apps catalog and video surveillance is a listed use case, but support is limited because there is no GPU or AI accelerator for detection.
The Mini X+ is an acceptable home lab machine. It supports Docker and virtual machines, has 2 x 10GbE, and takes up to 64GB of ECC memory, though it has no M.2 data slots.
The Mini X+ is acceptable for business storage. It has ECC memory, 7 hot-swap bays and 2 x 10GbE, with a 1-year warranty included.
We cannot confirm Creative AI on the Mini X+. GPU expansion is limited and Unverified, the PCIe 3.0 x4 slot is documented only for a 10G NIC, and there is no hardware acceleration.
Out of the box the TrueNAS Mini X+ has 32GB; the official ceiling is 64GB of DDR4 ECC with ECC support. A memory upgrade is the cheapest way to make it more useful for AI.
Working backwards from 64GB: 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 93B (Estimated).
ECC support protects against silent memory errors on a box that runs around the clock.
There is no supported way to add a GPU to the TrueNAS Mini X+: no PCIe slot and no OCuLink. Inference runs on the CPU, so keep to small models.
For a personal library, yes. A compact embedding model and a small chat model will run, but the TrueNAS Mini X+ is better as the document store behind a RAG system whose model runs on stronger hardware.
Built-in networking: 2 x 10GbE. Plenty for a shared knowledge base with several users.
| Configuration | RAM | SSD | Notes |
|---|---|---|---|
| 32GB, 2x10GbE | 32GB | None | Diskless. |
| 64GB, 2x10GbE | 64GB | None | Diskless. |
| 64GB, 2x10G SFP+ | 64GB | None | Diskless. |
The closest iXsystems model by bay count and AINAS Score. Only the specifications that differ are listed.
Its strongest AINAS profiles are Home Lab at 53 and Business at 53, 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.
Other AI Capable systems closest in overall score.
Yes at Q4, as an estimate. Llama 3.3 70B needs 43GB at Q4 and the Mini X+ takes up to 64GB, so it is the largest model listed on this page that fits (Estimated). At Q8 it needs 75GB and does not fit (Estimated). The processor is a CPU-only 8-core Atom, and Ollama support is limited, so treat this as a memory calculation, not a benchmark.
Yes. The Mini X+ ships with 32GB of DDR4 ECC memory and is upgradeable to 64GB. The memory is socketed rather than soldered. The sold configurations are 32GB and 64GB, so you can buy it at 64GB or expand later. Speed is not published by the manufacturer.
Yes. The Mini X+ uses DDR4 ECC memory, 32GB as supplied and 64GB at maximum. ECC suits a storage system where data integrity matters. It does not add AI capability, and the Atom C3758 still has no GPU or NPU.
No, not as documented. The Mini X+ has one PCIe 3.0 x4 slot in a compact chassis, and iXsystems documents it only for a 10G NIC. GPU use is unconfirmed. There is no OCuLink, Thunderbolt or USB4 port for an external GPU.
No, not for data. Only an internal M.2 boot device slot is documented, so the Mini X+ has 0 NVMe data slots. Storage comes from 7 SATA bays, 5 x 3.5in and 2 x 2.5in SSD, all hot-swap.
Yes to both. TrueNAS on the Mini X+ supports Apps, virtual machines and custom Docker images. The TrueNAS Apps catalog lists Open WebUI, vendor confirmed, along with Ollama, Immich and Frigate on its community train, all running on the 8-core Atom C3758 without a GPU. With 32GB of ECC memory as supplied, there is room for several apps alongside storage, and the 64GB ceiling leaves space for a CPU-only model as well.
Partly. Ollama support is documented by the manufacturer. See the capability table above for the source.
Yes. 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 documented by the manufacturer. See the capability table above for the source.
It has 2 x 10GbE built in, and the 1x PCIe 3.0 x4 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.