Raullenchai / Rapid MLX
Description
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.
Technical Specifications
| Core Language | |
| GitHub Authority | ⭐ 2801 stars |
| Last Code Push | 2026-06-15 |
| Open Issues / Bugs | 🛠️ 45 bugs listed |
| License Type | Open-Source (Free to use) |
Get Source Code
This project is open-source and hosted on GitHub. Click below to explore the repository, deployment guides, or fork the code.
Go to Repository →