The fastest local AI engine for Apple Silicon. 4.2x faster than Ollama, 0.08s cached TTFT, 100% tool calling. 17 tool parsers, prompt cache, reasoning separation, cloud routing. Drop-in OpenAI replacement. Works with Claude Code, Cursor, Aider.
Pulse
0
Velocity
Stars
1,563
Fastest local AI engine for Apple Silicon, 4.2x faster than Ollama.
Runs AI models locally on Mac hardware with impressive speed improvements.
Achieve 4.2x faster AI inference on your Mac with its dedicated engine.
Why Trending
Blazing fast AI inference on Apple Silicon, offering significant speedups over competitors.
Target Audience
Developers seeking performant local AI on Apple Silicon.
Similar Projects