The local translation in Firefox is an NMT model, not an LLM: https://github.com/mozilla/firefox-translations-models?tab=r...
It's much more efficient on system resources than the larger LLMs downloaded by browsers for other tasks.
Thanks for clarification!
It's still a transformer architecture though, right?
AFAIK the model for tab group suggestions is about the same size? (And I think that model is/can be used for other features as well?)