64GB max RAM · 4 bays · 2 x 2.5GbE
AINAS Score 50
$399.00
Amazon US · Verified
Ships from the US; delivery and import charges shown at checkout

AI ReadyASUSTORDiscontinued
Why AI Ready: Intel Xeon E-2224 (4 cores, no iGPU, no NPU) with three PCIe 3.0 slots and a 128GB memory ceiling meets the Xeon rule for AI Ready; no vendor-documented GPU path (slots listed for NIC and SAS cards), so not native.
Updated
Can the ASUSTOR Lockerstor 16R Pro (AS7116RDX) run local AI?
Partly. The ASUSTOR Lockerstor 16R Pro (AS7116RDX) runs local models on Intel Xeon E-2224 alone, and its 128GB ceiling allows 70B class models at higher-quality quantization, or large mixture-of-experts models at 4-bit (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 documented by the manufacturer.
The Lockerstor 16R Pro suits buyers who want a rackmount NAS with 16 bays that can also host a CPU-only local AI stack. It has an Intel Xeon E-2224 with 4 cores, 8GB of ECC DDR4-2666 memory as shipped and a 128GB ceiling. Memory is expandable. ADM 5 supports Docker and VirtualBox, and the Ollama + Open WebUI app lists the AS71 series as supported (Vendor confirmed). Three PCIe 3.0 slots take optional 10/25/40/50GbE and SAS cards. It has 2 M.2 slots, 550W redundant power supplies and a 5 year warranty. Mistral Large 2 123B fits at Q4 (Estimated), so memory is rarely the limit. The AINAS Score is 49.
The main problem is that the Lockerstor 16R Pro has no GPU path. ASUSTOR states its NAS models have no discrete GPU, and the PCIe slots are documented for network and SAS cards only. The Xeon has no integrated graphics and there is no NPU. Anyone who wants inference at a usable pace should look for a system with a documented GPU slot, an integrated GPU or an NPU with a stated TOPS figure. ASUSTOR itself recommends an external GPU host for inference. ASUSTOR has also discontinued the Lockerstor 16R Pro, though its status page shows software support as ongoing.
No verified price
We have not verified a listing for the ASUSTOR Lockerstor 16R Pro (AS7116RDX) 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 | Vendor confirmed | ASUSTOR App Central lists Ollama + Open WebUI (v0.11.4.r01, ADM 5.0+) for the AS71 series. CPU-only inference on Intel Xeon E-2224. ASUSTOR recommends an external GPU host for inference. |
| Ollama | Yes | Vendor confirmed | Ollama + Open WebUI app lists AS71 as a supported series. |
| Open WebUI | Yes | Vendor confirmed | Bundled with the Ollama + Open WebUI App Central package. |
| RAG | Limited | Vendor confirmed | ASUSTOR markets NAS as RAG knowledge base storage with vector databases (Chroma, pgvector, Weaviate) via Docker. It recommends an external compute host for inference. |
| AI search | No | Unverified | No AI or semantic file search feature found in ADM 5.1 material. |
| GPU expansion | No | Vendor confirmed | ASUSTOR states its NAS models do not feature a discrete GPU. PCIe slots are documented for network and SAS cards only on the spec page. |
| Hardware acceleration | No | Unverified | Intel ARK lists no processor graphics and no Quick Sync on the Xeon E-2224. ASUSTOR spec lists multimedia output N/A. No NPU. |
| AI photos | Yes | Vendor confirmed | Photo Gallery app lists AS71; ADM 5.1 adds facial recognition grouping powered by locally run AI. |
| AI video | No | Unverified | No AI video feature found in ADM documentation. |
| Surveillance AI | Yes | Vendor confirmed | Surveillance Center apps (1663 and 1661) list AS71; 4 free camera licences, more purchasable, per spec page. |
Calculated from the Lockerstor 16R Pro (AS7116RDX)'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 Lockerstor 16R Pro (AS7116RDX)'s use-case scores and capability rows. Unknown means we cannot confirm it, not that it probably works.
The Lockerstor 16R Pro is an OK choice for local LLMs. ASUSTOR lists Ollama + Open WebUI for it (Vendor confirmed), but local LLM support is limited to CPU-only inference on the Xeon E-2224.
Private RAG is OK on this system. ASUSTOR describes vector databases such as Chroma, pgvector and Weaviate running through Docker, which the system supports, though RAG support is limited and inference should run on an external host.
AI search is poor on the Lockerstor 16R Pro. No AI or semantic file search feature was found in ADM 5.1 material, and that finding is Unverified, so treat it as unconfirmed rather than supported.
AI photos are OK here. The Photo Gallery app lists the AS71 series, and ADM 5.1 adds facial recognition grouping powered by locally run AI (Vendor confirmed).
Surveillance is OK on the Lockerstor 16R Pro. Surveillance Center apps list the AS71 series (Vendor confirmed), with 4 free camera licences and extra licences sold separately.
Home lab use is OK. Docker and VirtualBox are both supported, memory can grow to 128GB of ECC, and three PCIe 3.0 slots accept network and SAS cards.
Business use is OK. It offers 16 bays, ECC memory, redundant power supplies and a 5 year warranty, though the model is discontinued, which matters for long-term planning.
Creative AI is rated OK, but only for CPU work. GPU expansion is not supported (Vendor confirmed) and hardware acceleration is unconfirmed, with no Quick Sync or graphics on the Xeon E-2224.
Out of the box the Lockerstor 16R Pro (AS7116RDX) has 8GB; the official ceiling is 128GB of DDR4-2666 ECC UDIMM with ECC support. A memory upgrade is the cheapest way to make it more useful for AI.
Working backwards from 128GB: 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 200B (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 Lockerstor 16R Pro (AS7116RDX): 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 Lockerstor 16R Pro (AS7116RDX) is better as the document store behind a RAG system whose model runs on stronger hardware.
Built-in networking: 4 x 1GbE. Adequate for a household, slower for bulk indexing.
| Configuration | RAM | SSD | Notes |
|---|---|---|---|
| 8GB | 8GB | None | Diskless; 1x 8GB ECC DDR4 pre-installed, 4 slots. |
The closest ASUSTOR model by bay count and AINAS Score. Only the specifications that differ are listed.
See the full ASUSTOR Lockerstor 12R Pro Gen2 (AS7212RDX) page
Its strongest AINAS profiles are Home Lab at 54 and RAG 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, or teams moving large files over the network every day.
Other AI Ready systems closest in overall score.
Yes, at Q4 only. Mistral Large 2 123B needs 73GB at Q4 and fits with the 128GB memory ceiling (Estimated). At Q8 it needs 130GB and does not fit (Estimated). Qwen3 235B A22B does not fit at either level (Estimated). These are memory calculations, not benchmarks, and inference would be CPU-only.
Yes. It ships with one 8GB ECC DDR4-2666 UDIMM and has 4 slots. The maximum is 128GB. Because the memory is ECC UDIMM, you need compatible ECC modules.
No. ASUSTOR states its NAS models do not feature a discrete GPU, and the three PCIe 3.0 slots are documented for network and SAS cards only (Vendor confirmed). There is no OCuLink, Thunderbolt or USB4 port for an external GPU either.
Yes to both. ADM 5 supports Docker Engine and VirtualBox on the AS71 series, and ASUSTOR's status page shows software support for the model as ongoing even though it is discontinued. The Ollama + Open WebUI app lists this series and is vendor confirmed, though inference is CPU-only on the 4-core Xeon E-2224. With up to 128GB of ECC memory, the system has room for several containers and virtual machines at once, but only 4 cores to share between them.
Yes. It uses DDR4-2666 ECC UDIMM memory, and the 8GB module included is ECC. The Intel Xeon E-2224 supports it, and the system can be expanded to 128GB.
Yes, it has 2 M.2 NVMe slots alongside its 16 drive bays. Separately, three PCIe 3.0 slots (two x4 and one x8) take optional 10/25/40/50GbE and SAS cards.
Yes. 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.
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 not yet verified. See the capability table above for the source.
It has 4 x 1GbE built in, and the 2x PCIe 3.0 x4 (x4 link), 1x PCIe 3.0 x8 (x8 link); for optional 10/25/40/50GbE and SAS cards 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.