# Foundry Local — AI Compare Ninja

> Free runtime from Microsoft that lets developers build AI models into their own apps that run directly on the device.

## Overview
- **Category:** Local AI (Runtimes & servers)
- **Status:** Active · checked
- **Paid from:** Not verified for this market
- **Free access:** Free plan
- **Website:** https://www.foundrylocal.ai/
- **Canonical URL:** https://www.aicompare.ninja/en/tool/foundry-local

## What it does
- For Windows, macOS (Apple silicon) and Linux; per the vendor no Azure subscription and no per-token costs
- Automatically picks the device's NPU, graphics card or CPU, per the vendor
- Model catalog per the vendor includes GPT OSS, Qwen, DeepSeek, Mistral, Phi and Whisper, among others

## In brief
Foundry Local is for developers who want to ship an app with AI that runs on the user's own device. Per Microsoft, prompts and responses stay on the device, the app works offline and the runtime adds only about 20 MB to the app package. An optional local server is compatible with the OpenAI API.

Per the licence terms, the software may send diagnostic data to Microsoft; you can opt out of much of it, but not all. Each model is also covered by its own licence.


## Limits
Runs on your own computer; you only pay for hardware and power

## Pricing tiers
| Tier | Price | Period | What you get |
| --- | --- | --- | --- |
| Free | free | free | Runs on your own computer; you only pay for hardware and power |

## Sources
All details regarding plans, limits, and features are based on official vendor documentation and the primary sources verified below.

- https://www.foundrylocal.ai/
- https://learn.microsoft.com/en-us/azure/foundry-local/what-is-foundry-local
- https://github.com/microsoft/Foundry-Local

---
*Source: AI Compare Ninja (2026) - https://www.aicompare.ninja/en/tool/foundry-local*