API or serverSoftware development

mlx-serve

Run MLX and GGUF models locally on Apple Silicon Macs.

Stars
276
Forks
21
License
MIT
Updated
Updated Jul 14, 2026

Checking live repository facts…

Project overview

mlx-serve combines a native Zig inference server for Apple Silicon with the MLX Core menu-bar app. Users can download and manage MLX or GGUF models, chat from the terminal or desktop UI, use tool-calling and agent features, and connect existing clients through OpenAI-, Anthropic-, or Ollama-compatible APIs. It does not require Python or cloud inference, but it is specifically designed for Apple Silicon Macs and remains limited by the machine's available memory and compute.

Repository facts

Primary language
Zig
License
MIT
Repository updated
Jul 14, 2026
Default branch
main

Resource types

API or serverCLI app

Use cases

Software development

Platforms

Claude CodeCursor

Operating systems

macOS

Runtime

Command lineLocal

Protocols & integrations

Model Context Protocol

Capabilities

Tool use

Audience

Developers

Related projects

Browse more similar projects