Unverified50% confidenceFactExact time
Mistral Large 4's vision encoder has been reduced from 2.5 billion parameters in the previous generation to 1.6 billion parameters.
1
Sources
50%
Confidence
Long-term
Relevance
10/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedMistral Large 4 adopts a sparse Mixture of Experts (MoE) architecture, with 49 billion (49B) parameters actually activated during each inference.76% similarVerifiedMistral released Mistral Large 4, codenamed LeChunk, a trillion-parameter, natively multimodal MoE model with approximately 49 billion active parameters.74% similarUnverifiedBased on the repository naming convention A52B, it is speculated that Mistral Large 4 activates 52 billion parameters per forward pass, though an official full specification has not yet been released.69% similarUnverifiedMistral Large 4 scored only 38 points on the Artificial Analysis composite intelligence index, ranking sixth among open-source models after excluding closed-source models.67% similarVerifiedMistral 7B was released in September 2023, has 7.3 billion parameters, and outperformed competing models with parameter counts of up to 13 billion and even 34 billion on multiple benchmarks.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/999747API
curl https://kongchang.com/api/v1/knowledge/claims/999747MCP
get_claim(id=999747)