⭐ 1.4k stars💬 text generation🔧 Pythonintermediate📄 Apache-2.0🔄 2026-06-28
About
OpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) with continuous batching, MCP tool calling, and multimodal support. Native MLX backend, 400+ tok/s. Works with Claude Code.
⚡ Quick Start
git clone https://github.com/vllm-mlx.git🏷️ Topics
💻 Supported Platforms
mac
📋 Technical Details
- Repository
- waybarrios/vllm-mlx
- Language
- Python
- License
- Apache-2.0
- Stars
- 1,413
- Category
- text generation
- Difficulty
- intermediate
- Last Updated
- 2026-06-28
- Platforms
- mac
Frequently Asked Questions About vllm-mlx
What is vllm-mlx?
OpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) with continuous batching, MCP tool calling, and multimodal support. Native MLX backend, 400+ tok/s. Works with Claude Code.
How do I install vllm-mlx?
Run: git clone https://github.com/vllm-mlx.git
What are the system requirements for vllm-mlx?
vllm-mlx supports mac. It is written in Python and is best suited for intermediate-level users. The repository has 1,413+ stars on GitHub and is licensed under Apache-2.0.