20:10
2026-05-27
cryptobriefing.com
artificial-intelligence
MiniMax teases M3 model with 15.6x faster decoding speed boost
Shanghai-based AI firm MiniMax has teased its next-generation M3 model, claiming a 15.6x faster decoding speed and 9.7x faster prefill speed over its M2 model when processing 1M-token contexts, driven…