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
| Type | Local open-weight |
|---|---|
| Parameters | 228.7B total · MoE, — active |
| Architecture | minimax_m2 |
| Context window | 205K tokens |
| Knowledge cutoff | — |
| Modalities | text |
| Recommended backends | — |
| Minimum viable rig | — |
Benchmark scores
| GPQA Diamond | — |
|---|---|
| SWE-bench Verified | — |
| AIME | — |
| MMLU-Pro | — |
| BFCL v3 (tool use) | — |
| Composite score | — |
| Community rating | No reviews yet |
VRAM & disk per quantization
| Quant | VRAM | Disk | RAM | Context |
|---|---|---|---|---|
| Q4_K_M | 134.1 GB | 132.6 GB | — | 205K |
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