Run AI Locally.
No Setup Required.

The easiest way to run LLMs on your Mac. Open source, beginner-friendly, and powered by Apple's MLX framework.

Download for macOS Contact

Open Source (MIT) • v1.0 • Apple Silicon (M1/M2/M3/M4)

Tools Panel - Built-in tools for search, file operations, and more

Built-in Tools

Settings - Configure server, ports, and generation defaults

Flexible Settings

Setup Guide - Integrate with Cline, VS Code, and other AI assistants

Easy Integration

Blazing Fast Tokens/Sec

Built directly on Apple's MLX framework to deliver industry-leading inference speeds on M-series chips.

Native Feel

Built with SwiftUI for a truly Mac-like experience. Smooth animations, frosted glass, and seamless integration.

Open Source

Transparency is key. Inspect the code, contribute features, and run models with zero compiled secrets.

Benchmarks. Off the charts.

Leveraging the Neural Engine to deliver token generation speeds that leave others in the dust.

Generative Feedback (MLX) 92 tok/s
Standard Runtime 41 tok/s

Llama-3-8B-Instruct on MacBook Pro M3 Max

Run the best models.

🦙 Llama 3
🤖 Mistral
🧠 Gemma
🦅 Falcon
🔮 Phi-3
⚡ StarCoder

Get Started in Seconds

Download Generative Feedback and start running AI models locally. No account required.

Download for macOS

Requires macOS 14+ and Apple Silicon (M1/M2/M3/M4)