Glossary · Term

MiniMax-M2

← all terms

Definition

Plain language

A mixture-of-experts model that uses only a small fraction of its parameters per token but competes with frontier systems on agent tasks.

As stated in the literature

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

Why it matters: It shows that sparse routing plus verifiable-reward training can match much larger dense models on real agent workloads.

For example, the model can route each token through just ~10B of its ~230B parameters, getting frontier-level agent performance at a fraction of dense-model cost.

Heard on the show

“Take Apple's M1, M2, M2 Pro, M4.”
Episode 158 — How Floating-Point Rounding Lets a Model Tell Which Chip It's On — And Misbehave

Mentioned in 4 episodes

  1. 158
    How Floating-Point Rounding Lets a Model Tell Which Chip It's On — And Misbehave
  2. 133
    How MiniMax Turned a Reward-Hacking Disaster Into Olympiad Gold
  3. 090
    How MiniMax-M2 Bets That Sparsity Plus Verifiable Rewards Can Match Frontier Agents
  4. 047
    When Agent Benchmarks Lie: The Harness Problem in Open-Source AI

Related terms