Home› Projects› mlx-openai-server
mlx-openai-server
Python

mlx-openai-server

A high-performance API server that provides OpenAI-compatible endpoints for MLX models. Developed using Python and powered by the FastAPI framework, it provides an efficient, scalable, and user-friendly solution for running MLX-based vision and language models

by cubist38 · GitHub
352
Stars
67
Forks
MIT
License
2025
Created
1 mo ago
Last commit
apple-silicon
Category
Python
Language
apple-siliconcontinuous-batchingfastapiMITPython
View on GitHub
In plain words

Run local AI models for text, images, and audio using an API that mimics OpenAI's setup on your Apple computer.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
mlx-openai-server — GitHub preview card
📈 Star history
353352
2026-07-202026-08-31
📈 Track mlx-openai-server

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

A high-performance API server that provides OpenAI-compatible endpoints for MLX models. Developed using Python and powered by the FastAPI framework, it provides an efficient, scalable, and user-friendly solution for running MLX-based vision and language models

mlx-openai-server has 352 stars on GitHub. It has been forked 67 times. mlx-openai-server is written mainly in Python. It has been in active development since 2025. mlx-openai-server is available under the MIT license. Its main topics are apple-silicon, continuous-batching, fastapi, flux.

❓ Frequently asked questions

What is mlx-openai-server?

A high-performance API server that provides OpenAI-compatible endpoints for MLX models. Developed using Python and powered by the FastAPI framework, it provides an efficient, scalable, and user-friendly solution for running MLX-based vision and language models

Is mlx-openai-server open source?

mlx-openai-server is an open-source project. It is released under the MIT license.

Is mlx-openai-server free?

Yes. mlx-openai-server is free and open source — you can use, modify and self-host it.

What license does mlx-openai-server use?

mlx-openai-server is available under the MIT license.

What language is mlx-openai-server written in?

mlx-openai-server is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — mlx-openai-server

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=cubist38-mlx-openai-server)](https://olud.ai/project/cubist38-mlx-openai-server.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →
Flux.jl
Relax! Flux is the ML library that doesn't make you tensor
★ 4.7k · data-science
sharesflux
flux-krea
Official GitHub repository for FLUX.1 Krea [dev].
★ 364 · diffusion-models
sharesflux
nunchaku
[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Mo…
★ 3.9k · comfyui
sharesflux
pmetal
PMetal: high-performance Apple Silicon framework for local LLM inference, LoRA/QLoRA fine-tunin…
★ 305 · ai
sharesapple-silicon
mlx-serve
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. In…
★ 961 · agent
sharesapple-silicon
stable-diffusion.cpp
Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++
★ 6.5k · ai
sharesflux
comfyui_LLM_party
LLM Agent Framework in ComfyUI includes MCP sever, Omost,GPT-sovits, ChatTTS,GOT-OCR2.0, and FL…
★ 2.3k · agent
sharesflux
comfyUI-Realtime-Lora
Train and block edit and save LoRAs directly inside ComfyUI for Z-image, Flux Klein, SDXL, Flu…
★ 538 · ai
sharesflux
ZenCtrl
In-context subject-driven image generation while preserving foreground fidelity
★ 351 · diffusion-models
sharesflux
omlx
LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from th…
★ 21k · apple-silicon

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.