Guides
- User Guide4,279 words, about 19 min to read. Markdown
- Admin Guide7,854 words, about 34 min to read. Markdown
jundot/omlx
oMLX is a production-ready, OpenAI-compatible LLM inference server built for Apple Silicon Macs. It runs entirely on-device using Apple's MLX framework — no cloud API costs, no GPU required, no data leaving your machine.
Generated May 2026 from jundot/omlx at f4ed78d
AI-generated documentation. The library is checked by sampling (three repositories so far); this guide was not individually reviewed. Verify against the project before relying on it.
Source and caveats
Built from the public repository github.com/jundot/omlx at commit f4ed78d. Upstream may have moved on since.
Unofficial; not affiliated with or reviewed by the project. How the guides were made, and how they were checked: guide library.