SHSelfHostIndex
ML

MLX LM

Run and fine-tune LLMs locally on Apple Silicon with MLX

Self-Hosted AI ★ 7.3k stars Medium setup MIT

MLX LM is a Python package from Apple's MLX project for running and fine-tuning large language models efficiently on Apple Silicon. It provides a command-line interface and HTTP server for local text generation entirely on-device.

Official siteSource code

Key features

  • Native Apple Silicon inference
  • LoRA fine-tuning
  • OpenAI-compatible server
  • Model quantization

Strengths

  • Released under the MIT license
  • Mature project with 7.3k GitHub stars
  • Written in Python

Is MLX LM secure?

OSV.dev has no published security advisories for MLX LM's repository. No known vulnerabilities is not proof of security: it means none have been publicly catalogued.

Source: OSV.dev, checked 2026-10-14. How this is measured.

MLX LM replaces

Self-hosted OpenAI API alternatives

Health badge

Maintain MLX LM? Add its health score to your README. The badge links back to this page.

SelfHostIndex: 89 · excellent

Markdown
[![SelfHostIndex health score for MLX LM](https://selfhostindex.com/badge/mlx-lm.svg)](https://selfhostindex.com/app/mlx-lm/)
HTML
<a href="https://selfhostindex.com/app/mlx-lm/"><img src="https://selfhostindex.com/badge/mlx-lm.svg" alt="SelfHostIndex health score for MLX LM"></a>
reStructuredText
.. image:: https://selfhostindex.com/badge/mlx-lm.svg
   :alt: SelfHostIndex health score for MLX LM
   :target: https://selfhostindex.com/app/mlx-lm/

The score is recomputed on every nightly rebuild from public repository data — see how it is calculated.

Compare MLX LM

10 head-to-head comparisons.

Similar self-hosted ai apps