# MLX — Apple Silicon ML Framework

> MLX is an array framework for machine learning on Apple silicon by Apple Research. 24.9K+ GitHub stars. NumPy-like API, unified memory, lazy computation, autodiff. Python, C++, Swift. MIT licensed.

## Install

Save as a script file and run:

## Quick Use

```bash
# Install
pip install mlx

# Quick start — matrix multiply on Apple GPU
python -c "
import mlx.core as mx
a = mx.random.normal((512, 512))
b = mx.random.normal((512, 512))
c = a @ b
mx.eval(c)
print(f'Result shape: {c.shape}, device: Apple GPU')
"

# For LLM inference, install mlx-lm
pip install mlx-lm
mlx_lm.generate --model mlx-community/Llama-3.2-3B-Instruct-4bit --prompt "Hello"
```

---

## Intro

MLX is an array framework for machine learning on Apple silicon, developed by Apple machine learning research. With 24,900+ GitHub stars and MIT license, MLX provides a NumPy-like Python API with composable function transformations (autodiff, vectorization, optimization), lazy computation, dynamic graph construction, and a unified memory model — no manual data transfers between CPU and GPU. It supports Python, C++, C, and Swift, making it ideal for training and inference on Mac hardware.

**Best for**: ML researchers and developers running models locally on Apple silicon (M1/M2/M3/M4)
**Works with**: Claude Code, OpenAI Codex, Cursor, Gemini CLI, Windsurf
**Platforms**: macOS (Apple Silicon), Linux (CUDA/CPU)

---

## Key Features

- **NumPy-like API**: Familiar interface for Python ML developers
- **Unified memory**: No manual CPU↔GPU data transfers on Apple silicon
- **Lazy computation**: Operations evaluated only when needed
- **Composable transforms**: Autodiff, vectorization, and graph optimization
- **Multi-language**: Python, C++, C, and Swift bindings
- **mlx-lm**: Run and fine-tune LLMs locally on Mac (Llama, Mistral, Qwen, etc.)

---

### FAQ

**Q: What is MLX?**
A: MLX is Apple's open-source ML framework with 24.9K+ stars for running machine learning on Apple silicon. It provides a NumPy-like API with unified memory, lazy computation, and autodiff. MIT licensed.

**Q: How do I install MLX?**
A: Run `pip install mlx`. For LLM inference: `pip install mlx-lm`. Requires Apple silicon Mac (M1+) or Linux with CUDA.

---

## Source & Thanks

> Created by [Apple ML Research](https://github.com/ml-explore). Licensed under MIT.
> [ml-explore/mlx](https://github.com/ml-explore/mlx) — 24,900+ GitHub stars

---
Source: https://tokrepo.com/en/workflows/26aa1d66-a2da-4be3-9c4e-7c33a4e3c398
Author: Script Depot