{"library":"rapid-mlx","type":"library","category":null,"description":"Rapid-MLX provides AI inference on Apple Silicon with a drop-in OpenAI-compatible API. It claims 2-4x speedups over Ollama. Current version is 0.6.80, under active development with a weekly release cadence.","language":"python","status":"active","version":"0.6.80","tags":["mlx","apple-silicon","ai","inference","openai-compatible"],"last_verified":"Sun Jun 07","install":[{"cmd":"pip install rapid-mlx","imports":["from rapid_mlx import Model","from rapid_mlx import ChatCompletion"]}],"homepage":"https://github.com/raullenchai/Rapid-MLX","github":"https://github.com/raullenchai/Rapid-MLX","docs":null,"changelog":null,"pypi":null,"npm":null,"openapi_spec":null,"status_page":null,"smithery":null,"compatibility":null}