MiniMax M2.7

MiniMaxAI · released 2026-03-18 · other license

MiniMax-M2.7 (March 2026) is an open-weight 230B/10B-active reasoning MoE scoring 50 on Artificial Analysis's Intelligence Index (~5.0/10), among the leading open models for its size. Non-commercial license.

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 Diamond
SWE-bench Verified
AIME
MMLU-Pro
BFCL v3 (tool use)
Composite score
Community ratingNo reviews yet

VRAM & disk per quantization

QuantVRAMDiskRAMContext
Q4_K_M134.1 GB132.6 GB205K

Strengths & weaknesses

Strengths: Artificial Analysis Intelligence Index 50, well above the open-weight median; Efficient MoE (230B total / 10B active), 200K+ context, competitive pricing

Weaknesses: Non-commercial license; Verbose, slower output; few per-benchmark numbers published