Fossy
fossy
Back jundot/omlx
omlx

omlx

Alternative to OpenAI API

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

22k 1.9k
Apache-2.0
 last commit 2026-08-18
apple-siliconinference-serverllmmacosmlxopenai-api
Website Source
Share:

About

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

omlx website preview

Languages

Python80.6%Swift7.1%HTML5.3%C++2.8%JavaScript2.3%Metal0.7%Objective-C++0.7%CSS0.2%CMake0.1%Shell0.1%Ruby0%

Contributors30

jundot1862cfbraun85jonathan30838JimStenstrom36github-actions[bot]31ashhart20alytaphoenix19richgoodson19williamxie198919ethannortharc19popfido18faisal18ivaniguarans14latent-variable14+16

Free alternative to OpenAI API

omlx is a free, open-source alternative to OpenAI API. Here's why:

  • 🚀 Fast LLM Inference
  • 🔄 Continuous Batching
  • 💾 SSD Caching
  • 🍎 Apple Silicon Optimized
  • ⚙️ macOS Menu Control
See all open-source alternatives to OpenAI API
Comments Theme
Platforms
macOS
Install
pip
Keywords
apple-silicon
inference-server
llm
macos
mlx
openai-api
slug: omlx

Sponsored

Ad space
300 × 250 (IAB)
SponsorSponsorSponsorSponsor
Ad space
300 × 250 (IAB)
Ad space
300 × 250 (IAB)