MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.
-
280
MiniMax M1
π¬Generate code from text prompts
-
MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention
Paper β’ 2506.13585 β’ Published β’ 240 -
MiniMaxAI/MiniMax-M1-80k
Text Generation β’ 456B β’ Updated β’ 16.2k β’ β’ 594 -
MiniMaxAI/MiniMax-M1-40k
Text Generation β’ 456B β’ Updated β’ 9.96k β’ 161