Back to MiniMax M3 428B in the gallery

MiniMax

Native multimodal MiniMax model that adds sparse attention to an M2-style MoE backbone for 1M-token context.

MiniMax M3 428B architecture diagram
MiniMax M3 428B architecture diagram. Select the diagram to view it at full size.

Architecture and specifications

Scale
428B total, 23B active (5.4% active)
Context (tokens)
1,048,576
License
MiniMax Community License
Date
2026-06-13
Decoder type
Sparse MoE
Attention
GQA with QK-Norm and MiniMax Sparse Attention
Layer mix
3 full GQA + 57 MiniMax Sparse Attention
KV cache / token (bf16) info
120 KiB · Moderate
Key detail
Uses three dense prefix layers, then 57 sparse-attention MoE layers with 128 routed experts and 4 routed plus 1 shared expert active per token.

Training and benchmarks

Pretraining data
Not disclosed The release describes native multimodal pretraining but gives no token total for the production 428B model. MiniMax M3 release
Post-training methods
RL, Rejection sampling Proof and verifier experts use RL with generative judges. Rejection-sampled fine-tuning trains a repair expert. These experts enter M3's merged training; the complete recipe is unspecified. MiniMax MaxProof training details
AA Intelligence Index v5.0 info
Total score 18.7 Knowledge Work 23.9 Coding 13.9 Science 10.9 General 26.1
AA Intelligence Index v4.3.2 info
Total score 29.2 General 36.3 Scientific 21.3 Coding 24.6 Agents 30.7

Further reading and tools