Local model.

A local model is an AI you run on your own machine instead of someone else's. Claude, ChatGPT, and Gemini all live on someone else's servers, so every prompt you send gets processed in the cloud. A local model flips that. You run it yourself, and your data never leaves your network.

If you handle sensitive client data, or you just don't want every request going through a third party, that's the appeal. No cloud bills, no rate limits.

The tradeoff: you need decent hardware to run it, and it usually won't match the frontier models on raw quality. For a lot of everyday jobs, though, that gap doesn't matter.