# lmstudio-ai/mlx-engine

LM Studio Apple MLX engine

Repository: https://github.com/lmstudio-ai/mlx-engine
Canonical: https://ross.abutalabs.com/products/mlx-engine
Language: Python
License: MIT
License Family: permissive
Topics: mlx, python
Last push: 2026-08-24T15:37:57+00:00

## Health v2 (maintenance only)
Score: 67/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 35, longevity 49
- inputs: {"age_days": 695, "days_push": 9, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1165, forks 133 (observed 2026-08-28T04:03:50.006089+00:00)

## What it is
mlx-engine is the Apple MLX-based LLM inference engine that powers LM Studio on Mac, built on mlx-lm with support for vision models via mlx-vlm and structured output via Outlines. It can also be used standalone for model loading and text/vision inference on Apple Silicon.

## Use cases
- run local LLM inference on Apple Silicon Macs
- serve MLX models inside LM Studio
- run vision-language models like Pixtral locally on Mac
- generate structured JSON output from local LLMs
- test MLX model inference from the command line

## When to choose
- you want fast local LLM inference on Apple Silicon with MLX
- you use LM Studio on Mac and want to extend or understand its MLX engine
- you need vision model support with MLX

## When to avoid
- you need inference on NVIDIA GPUs or non-macOS platforms
- you need a production serving stack with OpenAI-compatible APIs out of the box
- you don't use macOS 14+ or Python 3.11

## Facets
- artifact type: library
- maturity: active
- function: llm-inference, machine-learning, sdk
- domain: large-language-models, machine-learning, developer-tools
- platform: python
- tags: mlx, apple-silicon, lm-studio, vision-models, structured-output, macos

## Member repositories
- lmstudio-ai/mlx-engine (main) score 67

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:50.006089+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:29:27.589334+00:00, confidence not recorded.
  - readme: https://github.com/lmstudio-ai/mlx-engine (fetched 2026-08-28T04:03:50.006089+00:00, sha dc2ff9c82341)
- Data as of 2026-08-30T08:39:29.467469+00:00.