mlx

SKILL.md

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.

| 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.

Ejecución y ajuste de LLM en Apple Silicon con MLX. Úselo cuando trabaje con modelos localmente en Mac, convierta modelos de Hugging Face al formato MLX, realice ajustes con LoRA/QLoRA en Apple Silicon o proporcione modelos a través de HTTP API. Fuente: itsmostafa/llm-engineering-skills.

Ver original