Skip to main content
Foundry Local logo Foundry Local logo

Foundry Local

Run AI models locally on your device. Foundry Local provides on-device inference with complete data privacy, no Azure subscription required.

Run Models Locally
Free to Use
Data Privacy

Get Started in Two Steps

Step 1: Install Foundry Local
brew install microsoft/foundrylocal/foundrylocal
Step 2: Run a model
foundry model run qwen2.5-0.5b
Docs Models

Run Microsoft AI locally with complete control

Foundry Local brings the power of Azure AI to your environment, with flexible deployment options and enterprise-grade security.

On-Device Inference

Run AI models directly on your device with no cloud dependencies or Azure subscription required

Optimized Performance

Powered by ONNX Runtime with hardware acceleration for CPUs, GPUs, and NPUs

OpenAI-Compatible API

Easy integration with existing applications using familiar OpenAI patterns

Multi-Language SDKs

Simple SDKs for Python, JavaScript, C#, and Rust to get started quickly with your applications