jundot/omlx

LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar

[view on github]last commit: Oct 20, 2026

stars

22,953

7d

+200

30d

+1,011

90d

+5,074

## star history

## found in

Awesome local LLM/Inference engines Awesome Open Source AI/Local / On-device Inference