GGUF
The single-file model format used by llama.cpp and the tools built on it, like Ollama and LM Studio. One .gguf file holds the weights, the quantization, and the metadata, so you download it and run. Recipe names like Q4_K_M describe how the layers were quantized inside it.
GGUF is the JPEG of model files: rarely the fastest thing on any one machine, and it opens everywhere. The file is memory-mapped, so loading it does not mean reading all 20 GB first.
If you own a Mac and an MLX build exists, take the MLX build. Otherwise take GGUF, and if you run a mix of machines take GGUF on all of them so you are comparing the same file.