LM Studio
A desktop app for running models locally: search a catalog, download a GGUF or MLX build, chat with it, and flip on a server that speaks the OpenAI-compatible API at http://127.0.0.1:1234. It is the version of this with no terminal in it, which is why most people start here.
The useful part is that it shows you what you are choosing. Every quantization of a model is listed with its file size and a note on whether it fits your machine, so the tradeoff in part 2 of this series is a dropdown rather than a theory.
It is closed source and maintained by a company, which is worth knowing when you build something on top of it.