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

Foundry Local

Free#22 of 59 in Local AI Model Runtimes

Foundry Local: A free Microsoft runtime for local chat, embeddings, transcription and model lifecycle control. Ranked #22 of 59 in Local AI Model Runtimes by our editors (6.4/10); pricing: Free plan; best for developers wanting a simple Microsoft local model service.

6.4/10Editor score
Foundry Local6.4 Visit Foundry Local

At a glance

  • Editor score
    6.4 / 10
  • Pricing
    Free plan
  • Best for
    Developers wanting a simple Microsoft local model service
  • Free plan
    Yes
  • Paid from
    Free
  • GPU acceleration
    Yes
  • Facts checked
    17 Nov 2026
  • Where it wins

    • Free runtime covers discovery, downloads, loading, unloading and removal
    • Supports chat streaming, embeddings, transcription and vision samples
    • SDKs, CLI management and optional OpenAI-compatible local REST service
  • Where it doesn't

    • CLI uses Microsoft Software License Terms while the SDK is MIT-licensed
    • Support channels are limited to documentation and community
    • OpenAI-compatible REST service is optional rather than the default interface

Our verdict on Foundry Local

Foundry Local is Microsoft’s runtime for running AI model inference on personal devices and embedding local models in applications. It is aimed at developers who want model lifecycle controls, application SDKs and local inference across Windows, Apple-silicon macOS and Linux. The runtime provides chat completion with streaming, text embedding generation, audio transcription with streaming support, and a vision/image-understanding sample through the Responses API. Its catalog and lifecycle tools cover model discovery, downloading, loading, unloading and removal.

The runtime is free, with no paid plan tiers described. Its ecosystem reach comes from SDKs for C, C++, C#, JavaScript, Python and Rust, plus an API surface for applications. A command-line interface supports model discovery, downloading, loading and interactive execution, while CLI commands also manage models and servers. Developers can optionally run an OpenAI-compatible local REST web service. Hardware acceleration is available through WinML and ONNX execution providers, and the category specifications identify GPU acceleration, multimodal support, an API server and a CLI interface.

Foundry Local fits teams that prefer Microsoft tooling and need a practical local runtime rather than a hosted-only service. The main setup work centers on choosing models, downloading them, managing their loaded state and selecting the SDK or optional local service interface that fits an application. Licensing requires attention: the SDK is MIT-licensed, while the CLI uses Microsoft Software License Terms. Documentation and community channels are the listed support options. Developers seeking a free local stack with broad language bindings, streaming APIs and hardware acceleration should consider it; teams requiring a single license model or vendor support channel beyond docs and community may prefer another runtime.

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

Foundry Local pricing

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

Foundry Local fact sheet

Free planYes
Paid fromFree
GPU accelerationYes
Multimodal supportYes
Local API serverYes
CLI interfaceYes
Deployment modeHybrid
Model formatsNot verified
DeploymentCloud, Desktop, Browser extension
PlatformsWindows, macOS, Linux
SupportDocs, Community
Built forSolo, Small business, Mid-market, Enterprise (editorial estimate)
PricingFree plan
Websitegithub.com
Facts checked17 Nov 2026

Alternatives to Foundry Local

See all Foundry Local alternatives →

Used Foundry Local? 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 Foundry Local 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 — Foundry Local 6.4/10

Foundry Local is listed in our Local AI Model Runtimes directory. Add the badge to your site — it links back to this page.

<a href="https://www.itechguides.com/products/foundry-local/"><img src="https://www.itechguides.com/best/badge/foundry-local.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