Ollama is a user-friendly UI for LLM inference. It is powered by llama.cpp (or a fork of it) which is more power-user oriented and requires command-line wrangling. GGML is the math library behind llama.cpp and GGUF is the associated file format used for storing LLM weights.

Ollama on MacOS is a one-click solution with stable obe-click updates. Happy so far. But the mlx support was the only missing piece for me.