Side-by-side comparison

Mozilla project that packages a model and llama.cpp into a single cross-platform executable.

Easiest way to pull and run open models locally behind an OpenAI-compatible API; the default local runtime.

C/C++ LLM inference engine behind GGUF and most local tools; runs on CPUs, Apple Silicon and GPUs.

Apple's array framework for machine learning on Apple Silicon, with mlx-lm for fast local LLMs.