Ollama

Ollama is an open-source tool for downloading and running open language models on your own machine. One command pulls a model and starts it, and a local API lets other tools talk to it. Many coding tools, including Continue, Aider and several editor extensions, can use an Ollama model in place of a hosted one.

Developers use it to keep code on their own hardware, to work offline, and to try different open coding models without paying per request. It runs on macOS, Windows and Linux, and uses a GPU when one is available.

Local models are usually smaller than the leading hosted ones, so expect weaker results on hard tasks. Check each model's license before using it at work, and check your hardware has enough memory for the model size you pick.