Get the latest tech news
Mistral Small 3
Apache 2.0, 81% MMLU, 150 tokens/s
Particularly, Mistral Small 3 has far fewer layers than competing models, substantially reducing the time per forward pass. Among many other things, expect small and large Mistral models with boosted reasoning capabilities in the coming weeks. These models will also be made available through a serverless API on la Plateforme, through our on-prem and VPC deployments, customisation and orchestration platform, and through our inference and cloud partners.
Or read this on Hacker News