Model Recipes
MiniMax

MiniMaxAI/MiniMax-M2.1

MiniMax M2.1 MoE language model (230B total / 10B active) for coding, agent toolchains, and long-context reasoning — native FP8 checkpoint

Updated M2 series MoE with strong SWE-Bench and Terminal-Bench performance, 196K context

View on HuggingFaceView on ModelScope
moe230B / 10B196,608 ctxvLLM 0.11.0+text
Guide