MiniMax, released 2026-02-12. Sparse MoE decoder, 230B total, 10B active, 192K context. Attention: GQA with QK-Norm.
Sparse MoEMiniMax 🇨🇳 · October 23, 2025
MiniMax M2 (230B)
MiniMax's flagship returns to full attention and looks like a leaner, sparser cousin of Qwen3.
Key detail
Uses per-layer QK-Norm, much sparser MoE routing than Qwen3, and MTP during training.Total params
230B
Active / token
10B
Context
192K
Fact sheet
- Scale
- 230B total, 10B active (4.3% active)
- Context window
- 196,608 tokens
- Decoder type
- Sparse MoE
- Attention
- GQA with QK-Norm and partial RoPE
- Layer mix
- 62 GQA
- KV cache / token (bf16)
- 248 KiB · High
- License
- Modified MIT License
- Released
Efficiency
Parameters active per token
4.3%
10B of 230B weights run for each token.
AA Intelligence Index v4.3.2
Source18.6
- Scientific
- 7.3
Architecture concepts
Sources & resources
Use the ← and → keys to step through releases.
Similar architectures
MiniMax, released 2026-03-18. Sparse MoE decoder, 230B total, 10B active, 192K context. Attention: GQA with QK-Norm.
Tencent, released 2026-04-23. Sparse MoE decoder, 295B total, 21B active, 256K context. Attention: GQA with QK-Norm.
Z.ai, released 2025-07-28. Sparse MoE decoder, 355B total, 32B active, 128K context. Attention: GQA with QK-Norm.