Mistral Small 3 is the most efficient and versatile model of Mistral. Pre-trained and instructed version, Apache 2.0, 24B, 81% MMLU, 150 token/s. No synthetic data so great base for anything reasoning.
No reviews yet
Used Mistral Small 3? Be the first to share an honest review and help others decide.
No questions yet
Curious about pricing, features, or fit? Ask the first question.