MiniMax · 2025-06 · Sparse MoE
MiniMax-M1
MiniMax-M1 is a grouped-query attention (GQA) transformer released by MiniMax in 2025-06, with 80 layers, hidden size 6144 and a context window of 10,240,000 tokens.
Layer stack
Linear ×70 Attention ×10 · Layers 80
Key facts
| Family | MiniMax |
|---|---|
| Released | 2025-06 |
| Params | 456 B |
| Active | 45.9 B |
| Context | 10,240,000 tokens |
| Attention | GQA (64:8) |
| Layers | 80 |
| Hidden | 6,144 |
| Heads | 64 |
| Vocab | 200,064 |
| Position | RoPE |
| Norm | RMSNorm |
| Activation | silu |
| Dtype | bf16 |
| Architecture class | MiniMaxForCausalLM |
Architecture overview
Attention
grouped-query attention (GQA) — 64 q-heads / 8 kv-heads. RoPE θ=10,000,000.
Feed-forward / MoE
It is a sparse mixture-of-experts with 32 routed experts and top-2 routing; about 45.9B parameters are active per token.
Field-level comparison
Compared against the previous model of the same lab; where none exists, against the structurally closest model. The ratio column is this model divided by the comparison model.
Full-field comparison vs predecessor MiniMax-Text-01
| Model | MiniMax-M1 | MiniMax-Text-01 | Ratio |
|---|---|---|---|
| model_type | minimax | minimax | ＝ |
| architectures | MiniMaxForCausalLM | MiniMaxForCausalLM | ＝ |
| hidden_size | 6144 | 6144 | ≈1 |
| num_hidden_layers | 80 | 80 | ≈1 |
| num_attention_heads | 64 | 64 | ≈1 |
| num_key_value_heads | 8 | 8 | ≈1 |
| head_dim | 128 | 128 | ≈1 |
| intermediate_size | 9216 | 9216 | ≈1 |
| hidden_act | silu | silu | ＝ |
| num_experts_per_tok | 2 | 2 | ≈1 |
| rope_theta | 10000000 | 10000000 | ≈1 |
| max_position_embeddings | 10240000 | 10240000 | ≈1 |
| rms_norm_eps | 0.00001 | 0.00001 | ≈1 |
| vocab_size | 200064 | 200064 | ≈1 |
| attention_dropout | 0 | 0 | ＝ |
| layer_types | linear_attention×70 + full_attention×10 | linear_attention×70 + full_attention×10 | ＝ |
| initializer_range | 0.02 | 0.02 | ≈1 |
| full_attn_alpha_factor | 3.5565588200778455 | 3.5565588200778455 | ≈1 |
| full_attn_beta_factor | 1 | 1 | ≈1 |
| linear_attn_alpha_factor | 3.5565588200778455 | 3.5565588200778455 | ≈1 |
| linear_attn_beta_factor | 1 | 1 | ≈1 |
| mlp_alpha_factor | 3.5565588200778455 | 3.5565588200778455 | ≈1 |
| mlp_beta_factor | 1 | 1 | ≈1 |
| num_local_experts | 32 | 32 | ≈1 |
| output_router_logits | false | false | ＝ |
| postnorm | true | true | ＝ |
Most similar architectures
- MiniMax-Text-01 (MiniMax, 2025-01) 1.000
- Qwen3 235B A22B (Qwen, 2025-04) 0.991
- GLM-4.6 (GLM, 2025-10) 0.990
- GLM-4.5 (GLM, 2025-07) 0.989
- Mixtral 8x22B (Mistral, 2024-04) 0.988
- GLM-4.5-Air (GLM, 2025-07) 0.984
Similarity values range from 0 (no shared categorical features) to 1 (identical profiles).
Raw config fields
34 fields
| architectures | MiniMaxForCausalLM |
|---|---|
| attention_dropout | 0 |
| layer_types | linear_attention×70 + full_attention×10 |
| head_dim | 128 |
| hidden_act | silu |
| hidden_size | 6144 |
| initializer_range | 0.02 |
| intermediate_size | 9216 |
| full_attn_alpha_factor | 3.5565588200778455 |
| full_attn_beta_factor | 1 |
| linear_attn_alpha_factor | 3.5565588200778455 |
| linear_attn_beta_factor | 1 |
| mlp_alpha_factor | 3.5565588200778455 |
| mlp_beta_factor | 1 |
| max_position_embeddings | 10240000 |
| model_type | minimax |
| num_attention_heads | 64 |
| num_experts_per_tok | 2 |
| num_hidden_layers | 80 |
| num_key_value_heads | 8 |
| num_local_experts | 32 |
| output_router_logits | false |
| postnorm | true |
| rms_norm_eps | 0.00001 |
| rope_theta | 10000000 |
| rotary_dim | 64 |
| router_aux_loss_coef | 0.001 |
| router_jitter_noise | 0 |
| shared_intermediate_size | 0 |
| shared_moe_mode | sigmoid |
| tie_word_embeddings | false |
| transformers_version | 4.45.2 |
| use_cache | true |
| vocab_size | 200064 |