Suggestions appear as you type. Use the up and down arrows to choose one and Enter to open it.

IREE

Free#28 of 39 in GPU Computing SDKs

IREE: An open-source ML compiler for portable deployment across CPUs, GPUs, and devices. Ranked #28 of 39 in GPU Computing SDKs by our editors (6.5/10); pricing: Free plan; best for portable ML compiler deployment.

6.5/10Editor score
IREE6.5 Visit IREE

At a glance

  • Editor score
    6.5 / 10
  • Pricing
    Free plan
  • Best for
    Portable ML compiler deployment
  • Free plan
    Yes
  • Paid from
    Free
  • GPU backends
    6 backends
  • Facts checked
    22 Nov 2026
  • Where it wins

    • Imports models from JAX, ONNX, PyTorch, TensorFlow, and TensorFlow Lite
    • Targets Vulkan, ROCm/HIP, CUDA, Metal, AMD AIE, and WebGPU GPUs
    • Produces ahead-of-time modules for mobile, bare-metal, and WebAssembly deployment
  • Where it doesn't

    • WebGPU support is documented as experimental
    • Support channels center on community resources and documentation
    • The broad target matrix requires platform-specific compilation choices

Our verdict on IREE

IREE is an open-source, retargetable MLIR-based compiler and runtime for machine-learning programs. It is aimed at teams that need to move models across CPUs, GPUs, mobile devices, embedded targets, desktops, cloud environments, or WebAssembly. The project combines compiler tools, runtime components, a low-level C API, language bindings, and Python-distributed packages, with deployment options that include self-hosted and mobile environments.

The published project model is open source with a free plan, so adoption does not depend on selecting a paid tier. Its importer coverage spans JAX, ONNX, PyTorch, TensorFlow, and TensorFlow Lite, giving teams several established model-entry points. On the output side, IREE uses LLVM for CPU compilation and supports multithreaded runtime devices. GPU targets include Vulkan, ROCm/HIP, CUDA, Metal, AMD AIE, and WebGPU, while architecture targets include ARM, x86, and RISC-V. This combination suits organizations standardizing one compilation workflow across varied hardware and software stacks.

A standout capability is ahead-of-time compilation into deployable modules, paired with low-level C access and bindings for other languages. That design fits constrained, embedded, mobile, and WebAssembly deployments where a packaged runtime is preferable to carrying a full training framework. The tradeoff is scope: teams must choose among multiple accelerator backends, deployment targets, and language interfaces, and WebGPU remains experimental. Support is provided through community and documentation channels. IREE is a strong fit for engineering groups building portable inference artifacts; teams seeking a narrowly focused runtime or a conventional commercial support model should consider alternatives.

Your product? Our editors can test IREE in depth and publish a review, labelled as paid · from $149/mo →

IREE pricing

Plans Free planFree Free to use — no paid tier required for the core job.
See plans on iree.dev

IREE fact sheet

Free planYes
Paid fromFree
Compiler toolchainYes
GPU backends6 backends
Supported platformsCross_platform
Accelerator APIsVulkan, ROCm/HIP, CUDA, Metal, AMD AIE, WebGPU
Supported languagesC/C++, Python
Architecture targetsARM, x86, RISC-V
Parallel librariesYes
DeploymentCloud, Self-hosted, Desktop, Mobile
PlatformsLinux, Windows, macOS, iOS, Android
SupportCommunity, Docs
Built forSmall business, Mid-market, Enterprise (editorial estimate)
Integrations5 integrations: JAX, ONNX, PyTorch, TensorFlow, TensorFlow Lite
PricingFree plan
Websiteiree.dev
Facts checked22 Nov 2026

IREE integrations

IREE lists 5 integrations on its own site.

  • JAX
  • ONNX
  • PyTorch
  • TensorFlow
  • TensorFlow Lite

Alternatives to IREE

See all IREE alternatives →

Used IREE? Be the first to review it

The editor score above is our own research. What this page doesn't have yet is a reader's view — what you used IREE for, what worked and what didn't. No stars are seeded and no review is paid for; an editor reads every one before it appears.

Write a reviewTwo minutes · verified accounts only · read by an editor before it appears

Reviews come only from verified accounts. Sign in or create an account first — your e-mail is never shown.

Your rating

0 characters · at least 80, up to 3,000

Posted from your verified account. Reviews appear after an editor reads them, usually within two working days.

Featured on iTechGuides

Featured on iTechGuides — IREE 6.5/10

IREE is listed in our GPU Computing SDKs directory. Add the badge to your site — it links back to this page.

<a href="https://www.itechguides.com/products/iree/"><img src="https://www.itechguides.com/best/badge/iree.svg" alt="Featured on iTechGuides" width="230" height="46"></a>

Reviewed by iTechGuides Editors · Editorial team · Updated Nov 2026

Advertiser disclosure: iTechGuides is reader-supported. Vendors can pay for top positions in our rankings and for a place on other products' pages, and we may earn a commission when you click some links. Bought places stand at the number bought; this page and our disclosure say so. Paying vendors may get a fuller, more detailed review from our editors, and that review can change their score. How we rank.

Last updated · How we research and update