Post by Mistral AI on X
Mistral AI@MistralAI
XIntroducing Small 3, our most efficient and versatile model yet! Pre-trained and instructed version, Apache 2.0, 24B, 81% MMLU, 150 tok/s. No synthetic data so great base for anything reasoning - happy building!
t.co
3.1K likes134 repliesPosted Jan 30, 2025