self-llm/models_mlx

This tutorial aims to help users deploy and use large models based on Apple's native framework MLX-LM, in order to fully utilize the performance of Apple M series chips for local inference.

🔧 Environment Setup

# Create Conda virtual environment
conda create -n mlx-lm python=3.11
conda activate mlx-lm
# Install dependencies
pip install -r requirements.txt

🚀 Supported Models

• Qwen3