Mistral Large 4

Mistral Large 4 is a state-of-the-art, open-weight, general-purpose multimodal model with a granular Mixture-of-Experts architecture. It features 52B active parameters and 1.05T total parameters, and a 1.6B vision encoder.
305 points by funnym0nk3y 9 hours ago docs.mistral.ai 89 comments

Summary

Mistral Large 4 introduces a cutting-edge multimodal model that combines advanced AI capabilities with an impressive architecture, boasting 52 billion active parameters. Its unique Mixture-of-Experts design enhances its performance across various tasks, making it a significant development in the field of artificial intelligence.

Comments (89 of ) ⌛

Loading more comments... ⌛
Scroll down to load more comments
No comments available.
Type to search HN and engineering blog articles
Press Escape to close  |  ↑↓ to navigate  |  Enter to open