AINAS
45Drives HL15 15-bay NAS

45Drives HL15

AI Ready45Drives

Why AI Ready: AMD EPYC 7252 to 7452 with no NPU or integrated GPU, PCIe 4.0 x16 slots taking a GPU up to 10.25in, and up to 512GB DDR4 from the store; 45Drives does not document GPU inference on this model, so it stays ready under the Xeon or EPYC rule.

Updated

Can the 45Drives HL15 run local AI?

Yes, the 45Drives HL15 can run local language models. It pairs AMD EPYC 7252, 7272, 7282 or 7452 with up to 512GB of memory, which suits 70B class models at higher-quality quantization, or large mixture-of-experts models at 4-bit (Estimated).

It also has a GPU path (PCIe x16 slot), so a graphics card can be added later for much faster inference.

Local LLM support is confirmed by community reports.

The short answer

The HL15 suits buyers who want a 15-bay storage server that can also host local models and containers. It has an AMD EPYC CPU (8 cores on the 7252), 16GB of DDR4 ECC-capable RDIMM or LRDIMM memory included and up to 512GB available. It has 2 x 10GbE and 2 OCuLink ports. Bays are 15 and there are 2 M.2 slots. It runs Rocky Linux 9 with Houston UI and manages containers through Podman. On model memory, the largest model listed on this page, Qwen3 235B A22B, fits at Q4 (Estimated). It scores 74 on the AINAS Score.

The main catch is the GPU path. The EPYC options have no integrated GPU and no NPU, so acceleration needs an added card. 45Drives does not document GPU inference on this model. The chassis takes GPUs up to 10.25in, confirmed by vendor staff, but no GPU is sold as a listed option. The working LLM setup we found is a community owner build on Proxmox, not the Rocky Linux 9 and Houston UI setup it comes with. Buyers who want a supported, ready-to-run AI box should look for a vendor-documented GPU option, an integrated GPU or an NPU. Buyers who are happy to fit and configure their own card will not be held back.

Current offers

No verified price

We have not verified a listing for the 45Drives HL15 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 EPYC 7252, 7272, 7282 or 7452
Source: Manufacturer
Included RAM
16GB DDR4 RDIMM or LRDIMM
Source: Manufacturer
Maximum RAM
512GB ECC
Source: Manufacturer
Networking
2 x 10GbE
Source: Manufacturer
PCIe
PCIe 4.0 x16 slots on ASRock ROMED8-2T; exact count not readable on the store listing, some drop to x8 when NVMe or OCuLink is in use
Source: Manufacturer
GPU expansion
PCIe x16 slot
Source: Official docs
OCuLink
2 ports
Source: Manufacturer
Power supply
1000W
Source: Manufacturer
OS
Rocky Linux 9 with Houston UI
Source: Manufacturer
Docker
Yes
VM support
Not stated
Released
2025
Segment
Rackmount

Can the HL15 run local LLMs?

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

CapabilitySupportedEvidenceNote
Local LLM YesCommunity confirmedOwner build dated 2026-08-16 adds an RTX 4070 Ti and runs Ollama with GPU passthrough on Proxmox. No 45Drives statement on LLM use.
Ollama YesCommunity confirmedSame owner build runs Ollama in an LXC container. Not the stock OS.
Open WebUILimitedCommunity confirmedOwner build in the HL15 v1 form factor on the same ROMED8-2T board reports Open WebUI; seen in a search extract only.
RAGLimitedUnverifiedRunnable as containers in principle; no platform evidence found.
AI search NoUnverifiedNo AI search feature documented in Houston UI.
GPU expansion YesVendor confirmed45HomeLab staff state the 4U chassis fits GPUs up to 10.25in. No GPU is sold as a listed option in the fetched store data.
Hardware accelerationLimitedCommunity confirmedEPYC options list no integrated GPU, so acceleration needs an added card.
AI photosLimitedCommunity confirmedSame owner build runs Immich in an LXC container. No bundled photo app.
AI video NoUnverifiedNo AI video feature documented.
Surveillance AILimitedUnverifiedNo bundled surveillance software; self-hosted containers only, no evidence found.

What AI models can the HL15 run?

Calculated from the HL15'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, 23.6BQ8Yes38GBNot measuredEstimated
Gemma 3 27BGemma, 27BQ8Yes44GBNot measuredEstimated
Qwen3 30B A3BQwen, 30.5BQ8Yes47GBNot measuredEstimated
Qwen3 32BQwen, 32.8BQ8Yes50GBNot measuredEstimated
DeepSeek-R1 32B (Qwen distill)DeepSeek, 32.8BQ8Yes50GBNot measuredEstimated
Llama 3.3 70BLlama, 70.6BQ8Yes98GBNot measuredEstimated
Llama 4 Scout 17Bx16ELlama, 109BQ8Yes149GBNot measuredEstimated
Qwen2.5 72BQwen, 72.7BQ8Yes101GBNot measuredEstimated
Mistral Large 2 123BMistral, 123BQ8Yes164GBNot measuredEstimated

Workload fit

One verdict per workload, from the HL15's use-case scores and capability rows. Unknown means we cannot confirm it, not that it probably works.

Local LLMGood fit

The HL15 is a good fit for local LLMs. Community owners confirm Ollama with GPU passthrough on Proxmox, though 45Drives makes no statement on LLM use, and up to 512GB of memory holds large models (Estimated).

Private RAGOK

Private RAG is an acceptable fit on the HL15. The RAG row is unverified and limited, with no platform evidence, while Open WebUI is limited but community confirmed by an owner build on the same board.

AI searchPoor fit

AI search is a poor fit for the HL15. No AI search feature is documented in Houston UI, and that capability row is unverified and marked as not supported.

AI photosGood fit

AI photos work well on the HL15, with a caveat. An owner build runs Immich in an LXC container, community confirmed, but support is limited because there is no bundled photo app.

SurveillanceUnknown

We cannot confirm surveillance on the HL15. It ships with no bundled surveillance software, only self-hosted containers, and the capability row is unverified with no evidence found.

Home labGood fit

The HL15 is a good home lab machine. It has 15 bays, 2 x 10GbE, 2 M.2 slots, up to 512GB of ECC-capable DDR4 and Podman container management through Houston UI.

BusinessGood fit

The HL15 is a good fit for business use. It pairs an EPYC CPU with ECC-capable RDIMM or LRDIMM memory, 15 drive bays, 2 x 10GbE and a 1000W power supply in a rackmount chassis.

Creative AIGood fit

Creative AI is a good fit if you add a card. Vendor staff confirm GPU expansion up to 10.25in, but hardware acceleration is limited because the EPYC options have no integrated GPU.

How much RAM does the HL15 support?

The HL15 ships with 16GB of DDR4 RDIMM or LRDIMM and supports up to 512GB with ECC. Upgrading to the maximum lifts the model ceiling from 7B to 8B class models to 70B class models at higher-quality quantization, or large mixture-of-experts models at 4-bit (both Estimated).

As a rule of thumb, a 4-bit model needs about 0.6GB per billion parameters plus room for context. After leaving around 8GB for the NAS operating system, 512GB leaves space for a model of roughly 840B parameters at most (Estimated).

ECC memory support is a plus for always-on systems that also hold important files.

Can you add a GPU to the HL15?

Yes. The HL15 has a PCIe 4.0 x16 slots on ASRock ROMED8-2T; exact count not readable on the store listing, some drop to x8 when NVMe or OCuLink is in use that can take a graphics card. A discrete GPU with its own memory runs models far faster than CPU inference and lets the NAS serve several users at once. Check card length, height and power draw against the chassis and the 1000W power supply first.

It also has 2 OCuLink ports, a second route to an external GPU dock.

Is the HL15 suitable for RAG?

With limits. The HL15 can host a small RAG stack such as AnythingLLM or Open WebUI with a compact embedding model, but memory and compute restrict how large the answering model can be. It suits a personal document library more than a team knowledge base.

Networking is 2 x 10GbE. That is ample for indexing large libraries and for several people querying at once.

Limitations

  • No integrated GPU and no NPU. Acceleration needs an added graphics card, and no GPU is offered as a configuration option, so you supply your own.
  • 45Drives does not document GPU inference on the HL15. The working Ollama setups are community owner builds running Proxmox, not the Rocky Linux 9 and Houston UI setup it comes with.
  • The exact PCIe slot count is not recorded for the ASRock ROMED8-2T board, and some slots drop to x8 when NVMe or OCuLink is in use.
  • No warranty length is recorded for the HL15, and 512GB is the largest memory option offered rather than a confirmed board ceiling.
  • RAG, AI search and surveillance capabilities are Unverified, so treat them as unconfirmed rather than working features.

Which HL15 configurations are sold?

ConfigurationRAMSSDNotes
Fully Built, EPYC 7252, 16GB16GBNone
Fully Built, EPYC 7252, 64GB64GBNone
Fully Built, EPYC 7252, 128GB128GBNone

How is the HL15 different from the Storinator AV15?

The closest 45Drives model by bay count and AINAS Score. Only the specifications that differ are listed.

  • Processor: AMD EPYC 7252, 7272, 7282 or 7452 on the HL15, AMD EPYC 8124P, 8224P, 8324P or 8534P, or Intel Xeon Silver 4410Y, Gold 5418Y or Gold 6430 on the Storinator AV15
  • CPU cores: 8 on the HL15, 12 on the Storinator AV15
  • Memory fitted: 16GB on the HL15, none on the Storinator AV15
  • Memory ceiling: 512GB on the HL15, 2048GB on the Storinator AV15
  • M.2 slots: 2 on the HL15, 1 on the Storinator AV15
  • OCuLink: 2 on the HL15, none on the Storinator AV15
  • Power supply: 1000W on the HL15, 1400W on the Storinator AV15

See the full 45Drives Storinator AV15 page

Who should buy the HL15?

The HL15 scores best for Home Lab (82/100) and RAG (79/100). It suits home lab owners who want one box for storage, containers, media and a few AI services.

What are the alternatives to the HL15?

Other AI Ready systems closest in overall score.

Aoostar WTR Max

Aoostar WTR Max

Aoostar

AI Ready

128GB max RAM · 6 bays · 2 x 10GbE

AINAS Score 75

£774

Amazon UK · Verified

View

Where does the HL15 rank?

Workloads it suits

Common questions

Can the HL15 run Qwen3 235B A22B?

Yes, on memory alone. Qwen3 235B A22B needs 142GB at Q4 and the HL15 takes up to 512GB, so it fits at Q4 (Estimated). Q8 needs 250GB and also fits (Estimated). This is a calculation, not a benchmark. Running it in practice also needs software set up on the system, and a GPU would have to be added by you.

Can the HL15 take a graphics card?

Yes. Vendor staff state the 4U chassis fits GPUs up to 10.25in, and the board has PCIe 4.0 x16 slots. No GPU is sold as a listed option, so you would supply your own. Some slots drop to x8 when NVMe or OCuLink is in use.

Can you upgrade the memory in the HL15?

Yes. The memory is expandable rather than soldered. It includes 16GB and the largest configuration option is 512GB as DDR4 RDIMM or LRDIMM. The memory is ECC-capable, though 45Drives does not state ECC in words, so confidence is medium.

Can the HL15 connect to a GPU over OCuLink?

It has 2 OCuLink PCIe 4.0 x4 ports, so the connection is physically there. We found no confirmed external GPU setup over OCuLink. Using OCuLink can also drop some PCIe slots to x8.

Does the HL15 run Docker?

Not Docker itself. Houston UI manages Podman containers through cockpit-podman, and the HL15 runs Rocky Linux 9. Container support is recorded as present, with medium confidence. Community owners run Ollama and Immich in LXC containers on their own Proxmox builds, not on Rocky Linux 9 with Houston UI.

What configurations of the HL15 are recorded?

Three, all Fully Built with an AMD EPYC 7252: one with 16GB of memory, one with 64GB and one with 128GB. The CPU options also include the EPYC 7272, 7282 and 7452, and the largest memory option is 512GB as 8x 64GB DIMMs of DDR4 RDIMM or LRDIMM. The boot drive size is not recorded for these builds. Every build has 15 bays, 2 M.2 slots that take PCIe 4.0 x4 or SATA drives, 2 x 10GbE, 2 OCuLink ports and a 1000W power supply.

Can the HL15 run Ollama?

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

Does Open WebUI work on the HL15?

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

Does the HL15 do AI photo recognition?

Partly. AI photos support is confirmed by community reports. See the capability table above for the source.

Can the HL15 run AI surveillance?

Partly. Surveillance AI support is not yet verified. See the capability table above for the source.

Does the HL15 have hardware AI acceleration?

Partly. Hardware acceleration support is confirmed by community reports. See the capability table above for the source.

How fast is the HL15's network?

It has 2 x 10GbE built in, and the PCIe 4.0 x16 slots on ASRock ROMED8-2T; exact count not readable on the store listing, some drop to x8 when NVMe or OCuLink is in use can take a faster network card. The fastest port is 2 x 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.