MiniMax M2

MiniMaxAI · released 2025-10-23 · other license

MiniMax-M2 is a compact 230B-total/10B-active open-weight MoE (Oct 2025, MIT) for coding and agentic work. Artificial Analysis rates it above-average for its size (index 36), and it ranked #1 open-weight at launch on the v3.0 index.

Key specs

TypeLocal open-weight
Parameters228.7B total · MoE, — active
Architectureminimax_m2
Context window205K tokens
Knowledge cutoff
Modalitiestext
Recommended backends
Minimum viable rig

Benchmark scores

GPQA Diamond78%
SWE-bench Verified69.4%
AIME78%
MMLU-Pro82%
BFCL v3 (tool use)
Composite score6.38
Community ratingNo reviews yet

VRAM & disk per quantization

QuantVRAMDiskRAMContext
Q4_K_M134.1 GB132.6 GB205K

Strengths & weaknesses

Strengths: Highly efficient agentic/coding MoE (10B active of 230B); Top-tier open-weight coding (LiveCodeBench 83) at low cost; MIT license

Weaknesses: Low standalone reasoning without tools (HLE 12.5); Text-only, somewhat verbose