GitHub · Python
jundot/omlx
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
- Stars
- 23,761
- Forks
- 2,156
- Stars gained in 24 hours
- +58
- Forks gained in 24 hours
- +8
Topics: apple-silicon, inference-server, llm, macos, mlx, openai-api
Latest data point: Nov 20, 2026 · 23,761 stars · 2,156 forks