MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.
-
334
MiniMax M1
💬Generate code from text prompts
-
MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention
Paper • 2506.13585 • Published • 263 -
MiniMaxAI/MiniMax-M1-80k
Text Generation • 456B • Updated • 977 • • 671 -
MiniMaxAI/MiniMax-M1-40k
Text Generation • 456B • Updated • 25.9k • 175