MiniMaxAI/MiniMax-M3
MiniMax M3 vision-language MoE (427B total / 26B active) for frontier coding, agent toolchains, and 1M-token reasoning via MSA sparse attention — native multimodal (image + video + computer use); BF16 plus MXFP8 and AMD MI355X MXFP4 variants. Runs on NVIDIA (Hopper/Blackwell) and AMD CDNA4/CDNA3.
Frontier coding and agent (SWE-Bench Pro 59.0, Terminal-Bench 2.1 66.0); MSA sparse attention; 1M context