Home/Inference & Serving/mlx-serve

mlx-serve

ddalcu/mlx-serve

Native LLM inference server for Apple Silicon

GitHub Website

GraphCanon updated Aug 13, 2026 · GitHub synced Aug 13, 2026

40views this month

589 stars43 forksLast push Aug 12, 2026 Zig MIT

Decision brief

Focused on supporting Apple Silicon-powered macOS devices, mlx-serve provides a native and API-compatible inference service without requiring Python.

Good fit when

Use when your project requires running large language model (LLM) inferencing natively on Apple Silicon hardware.
Prefer this tool if your development environment is restricted to macOS systems and you aim for high performance.

Avoid when

Avoid if your infrastructure does not include devices with Apple Silicon chips, as it is specifically optimized for this architecture.
Do not use if you require cross-platform compatibility as mlx-serve targets macOS exclusively.

Requirements:: Requires Apple Silicon-powered macOS devices to ensure optimal performance and compatibility.

Observed Jul 17, 2026 · Source: enrich:decision_facts

mlx-serve alternatives Trust report

Verify the decision

Maintenance and security

Full trust report

Maintenance: Very active (0d since push); As of Jul 15, 2026
Provenance: Not a fork · Personal account; As of Jul 15, 2026
Security (OSV): No lockfile; As of Jul 15, 2026

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

git clone https://github.com/ddalcu/mlx-serve

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

llmfit

Hundreds of models & providers. One command to find what runs on your hardware.

32k★

omlx

LLM inference server with continuous batching and SSD caching for Apple Silicon

19k★

whichllm

Command-line tool to find and benchmark local LLM performance

6.2k★

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

Offers an OpenAI and Anthropic API-compatible inference server built in Zig for macOS devices with Apple Silicon chips, featuring an MLX Core app for chat and agent functionalities

Capability facts

Languages: zig
Source: github.language · Jul 17, 2026

README

Install via Homebrew License MIT, see LICENSE. mlx serve bundles third party code that stays under its own license, including some Apache 2.0 Metal kernels and the Jinja engine that renders chat templates. NOTICE lists all of it with the required attributions, and LICENSE APACHE...

For agents

This page has a .md twin and JSON over the API.

/tools/ddalcu-mlx-serve.md GET /api/graphcanon/tools/ddalcu-mlx-serve GET /api/graphcanon/graph?tool=ddalcu-mlx-serve