MiniMax
MiniMax M3 model Teased with 15.6X Decoding Speedup
MiniMax has teased its upcoming M3 model, featuring a custom sparse attention mechanism that delivers a 15.6x decoding speedup at a million tokens.
Zamil Safwan ·
MiniMax has teased its upcoming M3 model, featuring a custom sparse attention mechanism that delivers a 15.6x decoding speedup at a million tokens.
Zamil Safwan ·
