vllm-mlx
High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.
waybarrios/vllm-mlx
View on GitHub ↗High-performance OpenAI and Anthropic compatible LLM inference server for Apple Silicon. Native MLX, continuous batching, multimodal models, MCP tool calling, and Claude Code support.
vllm-mlx grew +2.8% in the last 30 days, ranks 104th of 490 in Local Runtime / Inference Engine, actively maintained, last commit 2 days ago.
Star trajectory
123 days tracked+2.8% in 30d, above the Local Runtime / Inference Engine median of +1.7%.
Last commit 2 days ago, fresher than the median of 5.5d.
How it compares in Local Runtime / Inference Engine
Ranked 104th of 490 by stars.
- Language
- Python
- License
- Apache License 2.0
- Contributors
- 66
- Forks
- 232
- Watchers
- 11
- Open issues
- 66
- Releases
- 16
- Created
- 2025-12-06
- Stars this week
- +10
You've seen where vllm-mlx stands today.
Get the moves before everyone else: the 5 Local Runtime / Inference Engine repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.