Back to directory
Mlx Omni Server
Free721MLX Omni Server is a local inference server powered by Apple's MLX framework, specifically designed for Apple Silicon (M
About
This local inference server runs on Apple Silicon chips using MLX framework. It provides OpenAI-compatible API endpoints, so you can use existing OpenAI tools without changes. Built for developers who want to run language models locally on their Mac.
Key Features
- function-calling
- genai
- mlx
- openai
- openai-api
Pricing
FreeOpen source. You supply your own LLM API keys.
Categories
DevOpsCoding