Sparse Attention
MiniMax Launches M3 Multimodal Foundation Model with 1M Context Window
MiniMax has officially launched its M3 multimodal foundation model, featuring a 1 million token context window and 15.6x faster decoding speeds.
Mohamed Ghamdi ·
MiniMax has officially launched its M3 multimodal foundation model, featuring a 1 million token context window and 15.6x faster decoding speeds.
Mohamed Ghamdi ·