Mistral Large 4, nicknamed "le Chonk," features a fine-grained mixture-of-experts architecture with 1.05 trillion total parameters, a 1.6 billion parameter vision encoder, and a one million token context window
Agree
Disagree
Overview
Debates
Related claims
Topics
Sources
5
52c7ae14
Multimodal models
119
claims
·
29
news stories
0
B
b5a31f81
Topic
Long context models
114
claims
·
9
news stories
0
B
b5a31f81
Topic
Mixture of experts (MoE)
59
claims
·
9
news stories
0