mlx
Running and fine-tuning LLMs on Apple Silicon with MLX. Use when working with models locally on Mac, converting Hugging Face models to MLX format, fine-tuning with LoRA/QLoRA on Apple Silicon, or serving models via HTTP API.
npx skills add majiayu000/claude-skill-registry --skill mlx --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Using MLX for LLMs on Apple Silicon MLX-LM is a Python package for running large language models on Apple Silicon, leveraging the MLX framework for optimized performance with unified memory architecture. ## Table of Contents - [Core Concepts](#core-concepts) - [Installation](#installation) - [Text Generation](#text-generation) - [Interactive Chat](#interactive-chat) - [Model Conversion](#model-conversion) - [Quantization](#quantization) - [Fine-tuning with LoRA](#fine-tuning-with-lora) - [Serving Models](#serving-models) - [Best Practices](#best-practices) - [References](#references) ## Core Concepts ### Why MLX | Aspect | PyTorch on Mac | MLX | |--------|----------------|-----| | Memory | Separate CPU/GPU copies | Unified memory, no copies | | Optimization | Generic Metal backend | Apple Silicon native | | Model loading | Slower, more memory | Lazy loading, efficient | | Quantization | Limited support | Built-in 4/8-bit | MLX arrays live in shared memory, accessible by both CPU and GPU without data transfer overhead. ### Supported Models MLX-LM supports most popular architectures: Llama, Mistral, Qwen, Phi, Gemma, Cohere, and many more. Check the [mlx-community](https://huggingf
- Table of Contents
- Core Concepts
- Why MLX
- Supported Models
- Installation
- Text Generation
- Python API
- Streaming Generation
- Batch Generation
- CLI Generation
- Interactive Chat
- CLI Chat
- Python Chat
- Model Conversion
pip install mlx-lm Basic generation mlx_lm.generate --model mlx-community/Llama-3.2-3B-Instruct-4bit \ With sampling parameters mlx_lm.generate --model mlx-community/Mistral-7B-Instruct-v0.3-4bit \ Start chat REPL (context preserved between turns) mlx_lm.chat --model mlx-community/Llama-3.2-3B-Instruct-4bit Convert with 4-bit quantization mlx_lm.convert --hf-path meta-llama/Llama-3.2-3B-Instruct \ With specific quantization
What does the mlx skill do?
Running and fine-tuning LLMs on Apple Silicon with MLX. Use when working with models locally on Mac, converting Hugging Face models to MLX format, fine-tuning with LoRA/QLoRA on Apple Silicon, or serving models via HTTP API.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill mlx --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.