Hunyuan · 2026-08 · Sparse MoE
Hunyuan 4 Preview
Hunyuan 4 Preview is a multi-head latent attention (MLA) transformer released by Hunyuan in 2026-08, with 78 layers, hidden size 6144 and a context window of 1,048,576 tokens.
Layer stack
sparse ×78 · Layers 78
Key facts
| Family | Hunyuan |
|---|---|
| Released | 2026-08 |
| Params | 770 B |
| Active | 49 B |
| Context | 1,048,576 tokens |
| Attention | MLA · kv_lora_rank 512 |
| Layers | 78 |
| Hidden | 6,144 |
| Heads | 64 |
| Vocab | 120,832 |
| Position | learned/absolute |
| Norm | RMSNorm |
| Activation | silu |
| Dtype | fp8 |
| Architecture class | HYV4ForCausalLM |
Architecture overview
Attention
multi-head latent attention (MLA). kv_lora_rank=512.
Feed-forward / MoE
It is a sparse mixture-of-experts with 256 routed experts and top-8 routing; about 49B parameters are active per token.
The configuration ships 1 extra multi-token-prediction (MTP) layers used to accelerate decoding.
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 Hunyuan 3
| Model | Hunyuan 4 Preview | Hunyuan 3 | Ratio |
|---|---|---|---|
| model_type | hy_v4 | hy_v3 | ≠ |
| architectures | HYV4ForCausalLM | HYV3ForCausalLM | ≠ |
| hidden_size | 6144 | 4096 | ×1.50 |
| num_hidden_layers | 78 | 80 | ×0.975 |
| num_attention_heads | 64 | 64 | ≈1 |
| num_key_value_heads | 8 | 8 | ≈1 |
| head_dim | 64 | 128 | ×0.500 |
| intermediate_size | 18432 | 13312 | ×1.38 |
| hidden_act | silu | silu | ＝ |
| n_routed_experts | 256 | — | |
| num_experts_per_tok | 8 | 8 | ≈1 |
| n_shared_experts | 1 | — | |
| moe_intermediate_size | 2048 | 1536 | ×1.33 |
| kv_lora_rank | 512 | — | |
| qk_rope_head_dim | 64 | — | |
| q_lora_rank | 2048 | — | |
| max_position_embeddings | 1048576 | 262144 | ×4.00 |
| rms_norm_eps | 0.00001 | 0.00001 | ≈1 |
| vocab_size | 120832 | 120832 | ≈1 |
| torch_dtype | bfloat16 | — | |
| num_nextn_predict_layers | 1 | 1 | ≈1 |
| attention_bias | false | — | |
| attention_dropout | 0 | — | |
| bitwise_backward_align | false | — | |
| bos_token_id | 120000 | 120000 | ≈1 |
| dtype | bfloat16 | bfloat16 | ＝ |
Most similar architectures
- GLM-5.2 (GLM, 2026-06) 1.000
- GLM-5.3 (GLM, 2026-08) 1.000
- GLM-5 (GLM, 2026-02) 0.999
- GLM-5.1 (GLM, 2026-04) 0.999
- GLM-5.3-Flash (GLM, 2026-08) 0.994
- Kimi K2 0905 (Kimi, 2025-09) 0.938
Similarity values range from 0 (no shared categorical features) to 1 (identical profiles).
Raw config fields
58 fields
| architectures | HYV4ForCausalLM |
|---|---|
| attention_bias | false |
| attention_dropout | 0 |
| bitwise_backward_align | false |
| bos_token_id | 120000 |
| dtype | bfloat16 |
| enable_ihc | true |
| enable_lm_head_fp32 | true |
| eos_token_id | 120025 |
| gated_mla | true |
| gating_type | elementwise |
| hc_eps | 0.000001 |
| hc_magnitude | 2 |
| hc_mult | 4 |
| head_dim | 64 |
| hidden_act | silu |
| hidden_size | 6144 |
| index_head_dim | 128 |
| index_n_heads | 32 |
| index_topk | 2048 |
| indexer_types | full×21 + shared×57 |
| initializer_range | 0.006 |
| intermediate_size | 18432 |
| kv_lora_rank | 512 |
| layer_types | deepseek_sparse_attention×78 |
| learnable_sink | true |
| learnable_sink_init | 0 |
| max_position_embeddings | 1048576 |
| mlp_layer_types | dense×1 + sparse×77 |
| model_type | hy_v4 |
| moe_intermediate_size | 2048 |
| mtp_loss_factor | 0.1 |
| n_group | 1 |
| n_routed_experts | 256 |
| n_shared_experts | 1 |
| norm_topk_prob | true |
| num_attention_heads | 64 |
| num_experts_per_tok | 8 |
| num_hidden_layers | 78 |
| num_key_value_heads | 8 |
| num_nextn_predict_layers | 1 |
| pad_token_id | 120002 |
| q_lora_rank | 2048 |
| qk_head_dim | 256 |
| qk_nope_head_dim | 192 |
| qk_rope_head_dim | 64 |
| rms_norm_eps | 0.00001 |
| routed_scaling_factor | 2.827 |
| swiglu_limit | 10 |
| tie_word_embeddings | false |
| topk_group | 1 |
| transformers_version | 5.16.2 |
| use_cache | true |
| use_dsa | true |
| use_mla | true |
| v_head_dim | 256 |
| vocab_size | 120832 |
| torch_dtype | bfloat16 |