Paradigm Launches Limite 1B Math Model Trained From Scratch on 300B Tokens

tensorqt · x · 2026-09-22

Paradigm introduced Limite 1B - Violetto, a model focused on "high-frequency mathematical intelligence" pre-trained from scratch on only 300B tokens. Reposting it, Dorialexander argues this shows Europe can build very good small models — and that they will keep growing.

Related event: Paradigm Releases First AI Model Limite 1B, a 1B Math-Focused Model(7 posts)→

Original post →

More from Models

Models channel →