ddalcu/mlx-serve
Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swift frontend macOS app with chat, music, voice, video generation.
- Stars
- 2.0k
- Forks
- 210
- Open issues
- 29
- Last push
- today
About mlx-serve
mlx-serve is a free, open-source LLM chat app by ddalcu, written mainly in Zig. Native LLM inference server for Apple Silicon. OpenAI + Anthropic API compatible. No Python. Zig backend, Swift frontend macOS app with chat, music, voice, video generation. It has 2.0k GitHub stars and 210 forks, and was last updated today. GitHub doesn't detect a standard license, so check the repository before using it commercially. According to the project, it works on macOS.
- License
- Not detected
- Language
- Zig
- Stars
- 2,025
- Last update
- today
- Runs on Mac
- Yes (as stated by the project)
- GPU
- Not stated
- Paid API key
- Not required
- Self-hostable
- Yes
Similar free tools
one-api37k stars · LLM API 管理 & 分发系统，支持 OpenAI、Azure、Anthropic Claude、Google Gemini、DeepSeek、字节豆包、ChatGLM、文心一言、讯飞星火、通义千问、360 智脑、腾讯混元等主流模型，统一 API 适配，可用于 key 管理与二次分发。单可执行文件，提供 Docker 镜像，一键部署，开箱即用。LLM API management & key
rtk84k stars · CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
unsloth78k stars · Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4, MiniMax-H3, Gemma 4, FLUX and more.
GPT_API_free45k stars · 免费大模型API，支持免费调用GPT、DeepSeek等主流模型，免费额度10000点，每日刷新！另付费价格最低官方1-2折！
omlx23k stars · LLM inference server with continuous batching & SSD caching for Apple Silicon — managed from the macOS menu bar
gpt4free67k stars · The official gpt4free repository | various collection of powerful language models | opus 4.6 gpt 5.3 kimi 2.5 deepseek v3.2 gemini 3
mlx-serve FAQ
Is mlx-serve free?
Yes. mlx-serve is open source and free to use. GitHub doesn't detect a standard license, so check the repository before using it commercially.
Does mlx-serve run on a Mac?
Yes. According to the project, mlx-serve works on macOS.
Does mlx-serve need a GPU?
The project doesn't state hardware needs. AI models generally run much faster with a GPU.
Is mlx-serve still maintained?
Yes. It was last updated today and has 29 open issues on GitHub.
What are alternatives to mlx-serve?
Similar free, open-source tools include one-api, rtk, unsloth, GPT_API_free.