🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// INFERENCE RUNTIME
MLX
Apple's array framework for machine learning on Apple Silicon. MLX-LM provides fast inference and fine-tuning for transformer models using unified memory. Optimal backend for Apple M-series chips.
- Platforms
- macOS
- Backends
- Metal (Apple Silicon only)
- Quant formats
- 4-bit, 8-bit, BF16, mixed-precision via mlx-lm
Videos about MLX
Apple Silicon MLX & LLM Inference: The Complete Guide
WWDC25: Explore large language models on Apple silicon with MLX | Apple
WWDC25: Get started with MLX for Apple silicon | Apple
FAQ
What platforms does MLX support?▶
MLX runs on macOS with backends Metal (Apple Silicon only).
What quant formats does MLX support?▶
MLX supports 4-bit, 8-bit, BF16, mixed-precision via mlx-lm.