MiniMaxAI/MiniMax-M2.5
Original228.7Bparameters
Fixture25.8Mparameters
Layer stacks1compared
Findings0to review
✓ Same architecture, smaller
Every module class, layer kind and checked property of the original is in the fixture.
Layer stacks
One square per layer, colored by kind: the layer's module classes and type attributes. Hover a square for its index and kind.
model.layers
Original · 62
Fixture · 2
| Kind | Original | Fixture | |
|---|---|---|---|
| DecoderLayer | 62 | 2 | ✓ kept |
Where the parameters are
Share of each model's parameters per component. Vocabulary and patch sizes are kept, so embeddings usually take a larger share of the fixture.
Original
Fixture
| Component | Original | Share | Fixture | Share |
|---|---|---|---|---|
| model.layers | 227.5B | 99.5% | 222.1K | 0.9% |
| lm_head | 614.6M | 0.3% | 12.8M | 49.6% |
| model.embed_tokens | 614.6M | 0.3% | 12.8M | 49.6% |
| model.norm | 3.1K | 0.0% | 64 | 0.0% |
Preserved properties
| Config | Property | Original | Fixture | |
|---|---|---|---|---|
| model | attention style | GQA (48 heads, 8 KV) | GQA (4 heads, 2 KV) | ✓ kept |
| model | MoE routing | top-8 of 256 experts | top-2 of 4 experts | ✓ kept |
| model | RoPE type | default | default | ✓ kept |
| model | model_type | minimax_m2 | minimax_m2 | ✓ kept |
| model | vocab_size | 200064 | 200064 | ✓ kept |
| model | tie_word_embeddings | False | False | ✓ kept |
| model | hidden_act | silu | silu | ✓ kept |
| model | max_position_embeddings | 196608 | 196608 | ✓ kept |
Module classes
Instances of each class in the built model (prefix MiniMaxM2 omitted).
| Class | Original | Fixture |
|---|---|---|
| Linear | 249 | 9 |
| RMSNorm | 249 | 9 |
| Attention | 62 | 2 |
| DecoderLayer | 62 | 2 |
| Experts | 62 | 2 |
| SparseMoeBlock | 62 | 2 |
| TopKRouter | 62 | 2 |
| SiLUActivation | 62 | 2 |
| Embedding | 1 | 1 |
| ForCausalLM | 1 | 1 |
| Model | 1 | 1 |
| RotaryEmbedding | 1 | 1 |
| ModuleList | 1 | 1 |
Config changes
10 fields changed, 34 unchanged.
| Field | Original | Fixture |
|---|---|---|
| attn_type_list | 62 entries: 62× 1 | [1, 1] |
| head_dim | 128 | 16 |
| hidden_size | 3072 | 64 |
| intermediate_size | 1536 | 128 |
| num_attention_heads | 48 | 4 |
| num_experts_per_tok | 8 | 2 |
| num_hidden_layers | 62 | 2 |
| num_key_value_heads | 8 | 2 |
| num_local_experts | 256 | 4 |
| quantization_config | {"activation_scheme": "dynamic", "fmt": "float8_e4m3fn", "quant_method": "fp8… | — |