Definition
A mixture-of-experts model that uses only a small fraction of its parameters per token but competes with frontier systems on agent tasks.
MiniMax's ~230B-parameter fine-grained mixture-of-experts model with ~10B active per token, optimized for agentic workloads via verifiable-reward data pipelines and the Forge training system.
Also called: MiniMax M2, M2, M2.5, M2.7