Models
Docs
Pricing
Sign in
Models
Docs
Pricing
Sign in
qwen3.5
:9b-mtp-nvfp4
21.5M
Downloads
Updated
4 minutes ago
Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.
Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.
Cancel
vision
tools
thinking
0.8b
2b
4b
9b
27b
35b
122b
qwen3.5:9b-mtp-nvfp4
...
/
json
b41ca2dedf68 · 42kB
{
"architectures": [
"Qwen3_5ForConditionalGeneration"
],
"image_token_id": 248056,
"model_type": "qwen3_5",
"text_config": {
"attention_bias": false,
"attention_dropout": 0.0,
"attn_output_gate": true,
"dtype": "bfloat16",
"eos_token_id": 248044,
"full_attention_interval": 4,
"head_dim": 256,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 12288,
"layer_types": [
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention"
],
"linear_conv_kernel_dim": 4,
"linear_key_head_dim": 128,
"linear_num_key_heads": 16,
"linear_num_value_heads": 32,
"linear_value_head_dim": 128,
"max_position_embeddings": 262144,
"mlp_only_layers": [],
"model_type": "qwen3_5_text",
"mtp_num_hidden_layers": 1,
"mtp_use_dedicated_embeddings": false,
"num_attention_heads": 16,
"num_hidden_layers": 32,
"num_key_value_heads": 4,
"rms_norm_eps": 1e-06,
"use_cache": true,
"vocab_size": 248320,
"mamba_ssm_dtype": "float32",
"rope_parameters": {
"mrope_interleaved": true,
"mrope_section": [
11,
11,
10
],
"rope_type": "default",
"rope_theta": 10000000,
"partial_rotary_factor": 0.25
}
},
"tie_word_embeddings": false,
"transformers_version": "4.57.0.dev0",
"video_token_id": 248057,
"vision_config": {
"deepstack_visual_indexes": [],
"depth": 27,
"hidden_act": "gelu_pytorch_tanh",
"hidden_size": 1152,
"in_channels": 3,
"initializer_range": 0.02,
"intermediate_size": 4304,
"model_type": "qwen3_5",
"num_heads": 16,
"num_position_embeddings": 2304,
"out_hidden_size": 4096,
"patch_size": 16,
"spatial_merge_size": 2,
"temporal_patch_size": 2
},
"vision_end_token_id": 248054,
"vision_start_token_id": 248053,
"quantization_config": {
"config_groups": {
"group_0": {
"input_activations": {
"dynamic": false,
"num_bits": 8,
"type": "float",
"group_size": 32
},
"weights": {
"dynamic": false,
"num_bits": 8,
"type": "float",
"group_size": 32
},
"targets": [
"lm_head",
"model.language_model.embed_tokens",
"model.language_model.layers.11.self_attn.k_proj",
"model.language_model.layers.11.self_attn.o_proj",
"model.language_model.layers.11.self_attn.q_proj",
"model.language_model.layers.11.self_attn.v_proj",
"model.language_model.layers.15.self_attn.k_proj",
"model.language_model.layers.15.self_attn.o_proj",
"model.language_model.layers.15.self_attn.q_proj",
"model.language_model.layers.15.self_attn.v_proj",
"model.language_model.layers.19.self_attn.k_proj",
"model.language_model.layers.19.self_attn.o_proj",
"model.language_model.layers.19.self_attn.q_proj",
"model.language_model.layers.19.self_attn.v_proj",
"model.language_model.layers.23.self_attn.k_proj",
"model.language_model.layers.23.self_attn.o_proj",
"model.language_model.layers.23.self_attn.q_proj",
"model.language_model.layers.23.self_attn.v_proj",
"model.language_model.layers.27.self_attn.k_proj",
"model.language_model.layers.27.self_attn.o_proj",
"model.language_model.layers.27.self_attn.q_proj",
"model.language_model.layers.27.self_attn.v_proj",
"model.language_model.layers.3.self_attn.k_proj",
"model.language_model.layers.3.self_attn.o_proj",
"model.language_model.layers.3.self_attn.q_proj",
"model.language_model.layers.3.self_attn.v_proj",
"model.language_model.layers.31.self_attn.k_proj",
"model.language_model.layers.31.self_attn.o_proj",
"model.language_model.layers.31.self_attn.q_proj",
"model.language_model.layers.31.self_attn.v_proj",
"model.language_model.layers.7.self_attn.k_proj",
"model.language_model.layers.7.self_attn.o_proj",
"model.language_model.layers.7.self_attn.q_proj",
"model.language_model.layers.7.self_attn.v_proj"
]
},
"group_1": {
"weights": {
"dynamic": false,
"num_bits": 4,
"type": "float",
"group_size": 16
},
"targets": [
"model.language_model.layers.0.linear_attn.in_proj_qkv",
"model.language_model.layers.0.linear_attn.in_proj_z",
"model.language_model.layers.0.linear_attn.out_proj",
"model.language_model.layers.0.mlp.down_proj",
"model.language_model.layers.0.mlp.gate_proj",
"model.language_model.layers.0.mlp.up_proj",
"model.language_model.layers.1.linear_attn.in_proj_qkv",
"model.language_model.layers.1.linear_attn.in_proj_z",
"model.language_model.layers.1.linear_attn.out_proj",
"model.language_model.layers.1.mlp.down_proj",
"model.language_model.layers.1.mlp.gate_proj",
"model.language_model.layers.1.mlp.up_proj",
"model.language_model.layers.10.linear_attn.in_proj_qkv",
"model.language_model.layers.10.linear_attn.in_proj_z",
"model.language_model.layers.10.linear_attn.out_proj",
"model.language_model.layers.10.mlp.down_proj",
"model.language_model.layers.10.mlp.gate_proj",
"model.language_model.layers.10.mlp.up_proj",
"model.language_model.layers.11.mlp.down_proj",
"model.language_model.layers.11.mlp.gate_proj",
"model.language_model.layers.11.mlp.up_proj",
"model.language_model.layers.12.linear_attn.in_proj_qkv",
"model.language_model.layers.12.linear_attn.in_proj_z",
"model.language_model.layers.12.linear_attn.out_proj",
"model.language_model.layers.12.mlp.down_proj",
"model.language_model.layers.12.mlp.gate_proj",
"model.language_model.layers.12.mlp.up_proj",
"model.language_model.layers.13.linear_attn.in_proj_qkv",
"model.language_model.layers.13.linear_attn.in_proj_z",
"model.language_model.layers.13.linear_attn.out_proj",
"model.language_model.layers.13.mlp.down_proj",
"model.language_model.layers.13.mlp.gate_proj",
"model.language_model.layers.13.mlp.up_proj",
"model.language_model.layers.14.linear_attn.in_proj_qkv",
"model.language_model.layers.14.linear_attn.in_proj_z",
"model.language_model.layers.14.linear_attn.out_proj",
"model.language_model.layers.14.mlp.down_proj",
"model.language_model.layers.14.mlp.gate_proj",
"model.language_model.layers.14.mlp.up_proj",
"model.language_model.layers.15.mlp.down_proj",
"model.language_model.layers.15.mlp.gate_proj",
"model.language_model.layers.15.mlp.up_proj",
"model.language_model.layers.16.linear_attn.in_proj_qkv",
"model.language_model.layers.16.linear_attn.in_proj_z",
"model.language_model.layers.16.linear_attn.out_proj",
"model.language_model.layers.16.mlp.down_proj",
"model.language_model.layers.16.mlp.gate_proj",
"model.language_model.layers.16.mlp.up_proj",
"model.language_model.layers.17.linear_attn.in_proj_qkv",
"model.language_model.layers.17.linear_attn.in_proj_z",
"model.language_model.layers.17.linear_attn.out_proj",
"model.language_model.layers.17.mlp.down_proj",
"model.language_model.layers.17.mlp.gate_proj",
"model.language_model.layers.17.mlp.up_proj",
"model.language_model.layers.18.linear_attn.in_proj_qkv",
"model.language_model.layers.18.linear_attn.in_proj_z",
"model.language_model.layers.18.linear_attn.out_proj",
"model.language_model.layers.18.mlp.down_proj",
"model.language_model.layers.18.mlp.gate_proj",
"model.language_model.layers.18.mlp.up_proj",
"model.language_model.layers.19.mlp.down_proj",
"model.language_model.layers.19.mlp.gate_proj",
"model.language_model.layers.19.mlp.up_proj",
"model.language_model.layers.2.linear_attn.in_proj_qkv",
"model.language_model.layers.2.linear_attn.in_proj_z",
"model.language_model.layers.2.linear_attn.out_proj",
"model.language_model.layers.2.mlp.down_proj",
"model.language_model.layers.2.mlp.gate_proj",
"model.language_model.layers.2.mlp.up_proj",
"model.language_model.layers.20.linear_attn.in_proj_qkv",
"model.language_model.layers.20.linear_attn.in_proj_z",
"model.language_model.layers.20.linear_attn.out_proj",
"model.language_model.layers.20.mlp.down_proj",
"model.language_model.layers.20.mlp.gate_proj",
"model.language_model.layers.20.mlp.up_proj",
"model.language_model.layers.21.linear_attn.in_proj_qkv",
"model.language_model.layers.21.linear_attn.in_proj_z",
"model.language_model.layers.21.linear_attn.out_proj",
"model.language_model.layers.21.mlp.down_proj",
"model.language_model.layers.21.mlp.gate_proj",
"model.language_model.layers.21.mlp.up_proj",
"model.language_model.layers.22.linear_attn.in_proj_qkv",
"model.language_model.layers.22.linear_attn.in_proj_z",
"model.language_model.layers.22.linear_attn.out_proj",
"model.language_model.layers.22.mlp.down_proj",
"model.language_model.layers.22.mlp.gate_proj",
"model.language_model.layers.22.mlp.up_proj",
"model.language_model.layers.23.mlp.down_proj",
"model.language_model.layers.23.mlp.gate_proj",
"model.language_model.layers.23.mlp.up_proj",
"model.language_model.layers.24.linear_attn.in_proj_qkv",
"model.language_model.layers.24.linear_attn.in_proj_z",
"model.language_model.layers.24.linear_attn.out_proj",
"model.language_model.layers.24.mlp.down_proj",
"model.language_model.layers.24.mlp.gate_proj",
"model.language_model.layers.24.mlp.up_proj",
"model.language_model.layers.25.linear_attn.in_proj_qkv",
"model.language_model.layers.25.linear_attn.in_proj_z",
"model.language_model.layers.25.linear_attn.out_proj",
"model.language_model.layers.25.mlp.down_proj",
"model.language_model.layers.25.mlp.gate_proj",
"model.language_model.layers.25.mlp.up_proj",
"model.language_model.layers.26.linear_attn.in_proj_qkv",
"model.language_model.layers.26.linear_attn.in_proj_z",
"model.language_model.layers.26.linear_attn.out_proj",
"model.language_model.layers.26.mlp.down_proj",
"model.language_model.layers.26.mlp.gate_proj",
"model.language_model.layers.26.mlp.up_proj",
"model.language_model.layers.27.mlp.down_proj",
"model.language_model.layers.27.mlp.gate_proj",
"model.language_model.layers.27.mlp.up_proj",
"model.language_model.layers.28.linear_attn.in_proj_qkv",
"model.language_model.layers.28.linear_attn.in_proj_z",
"model.language_model.layers.28.linear_attn.out_proj",
"model.language_model.layers.28.mlp.down_proj",
"model.language_model.layers.28.mlp.gate_proj",
"model.language_model.layers.28.mlp.up_proj",
"model.language_model.layers.29.linear_attn.in_proj_qkv",
"model.language_model.layers.29.linear_attn.in_proj_z",
"model.language_model.layers.29.linear_attn.out_proj",
"model.language_model.layers.29.mlp.down_proj",
"model.language_model.layers.29.mlp.gate_proj",
"model.language_model.layers.29.mlp.up_proj",
"model.language_model.layers.3.mlp.down_proj",
"model.language_model.layers.3.mlp.gate_proj",
"model.language_model.layers.3.mlp.up_proj",
"model.language_model.layers.30.linear_attn.in_proj_qkv",
"model.language_model.layers.30.linear_attn.in_proj_z",
"model.language_model.layers.30.linear_attn.out_proj",
"model.language_model.layers.30.mlp.down_proj",
"model.language_model.layers.30.mlp.gate_proj",
"model.language_model.layers.30.mlp.up_proj",
"model.language_model.layers.31.mlp.down_proj",
"model.language_model.layers.31.mlp.gate_proj",
"model.language_model.layers.31.mlp.up_proj",
"model.language_model.layers.4.linear_attn.in_proj_qkv",
"model.language_model.layers.4.linear_attn.in_proj_z",
"model.language_model.layers.4.linear_attn.out_proj",
"model.language_model.layers.4.mlp.down_proj",
"model.language_model.layers.4.mlp.gate_proj",
"model.language_model.layers.4.mlp.up_proj",
"model.language_model.layers.5.linear_attn.in_proj_qkv",
"model.language_model.layers.5.linear_attn.in_proj_z",
"model.language_model.layers.5.linear_attn.out_proj",
"model.language_model.layers.5.mlp.down_proj",
"model.language_model.layers.5.mlp.gate_proj",
"model.language_model.layers.5.mlp.up_proj",
"model.language_model.layers.6.linear_attn.in_proj_qkv",
"model.language_model.layers.6.linear_attn.in_proj_z",
"model.language_model.layers.6.linear_attn.out_proj",
"model.language_model.layers.6.mlp.down_proj",
"model.language_model.layers.6.mlp.gate_proj",
"model.language_model.layers.6.mlp.up_proj",
"model.language_model.layers.7.mlp.down_proj",
"model.language_model.layers.7.mlp.gate_proj",
"model.language_model.layers.7.mlp.up_proj",
"model.language_model.layers.8.linear_attn.in_proj_qkv",
"model.language_model.layers.8.linear_attn.in_proj_z",
"model.language_model.layers.8.linear_attn.out_proj",
"model.language_model.layers.8.mlp.down_proj",
"model.language_model.layers.8.mlp.gate_proj",
"model.language_model.layers.8.mlp.up_proj",
"model.language_model.layers.9.linear_attn.in_proj_qkv",
"model.language_model.layers.9.linear_attn.in_proj_z",
"model.language_model.layers.9.linear_attn.out_proj",
"model.language_model.layers.9.mlp.down_proj",
"model.language_model.layers.9.mlp.gate_proj",
"model.language_model.layers.9.mlp.up_proj"
]
}
},
"quantized_layers": {
"model.language_model.embed_tokens": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.0.linear_attn.out_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.0.linear_attn.in_proj_qkv": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.0.linear_attn.in_proj_z": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.0.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.0.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.0.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.linear_attn.out_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.linear_attn.in_proj_qkv": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.linear_attn.in_proj_z": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.1.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.2.linear_attn.out_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.2.linear_attn.in_proj_qkv": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.2.linear_attn.in_proj_z": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.2.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.2.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.2.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.3.self_attn.q_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.3.self_attn.k_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.3.self_attn.v_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.3.self_attn.o_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.3.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.3.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.3.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.4.linear_attn.out_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.4.linear_attn.in_proj_qkv": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.4.linear_attn.in_proj_z": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.4.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.4.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.4.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.5.linear_attn.out_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.5.linear_attn.in_proj_qkv": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.5.linear_attn.in_proj_z": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.5.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.5.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.5.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.6.linear_attn.out_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.6.linear_attn.in_proj_qkv": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.6.linear_attn.in_proj_z": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.6.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.6.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.6.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.7.self_attn.q_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.7.self_attn.k_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.7.self_attn.v_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.7.self_attn.o_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.7.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.7.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.7.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.8.linear_attn.out_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.8.linear_attn.in_proj_qkv": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.8.linear_attn.in_proj_z": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.8.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.8.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.8.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.9.linear_attn.out_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.9.linear_attn.in_proj_qkv": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.9.linear_attn.in_proj_z": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.9.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.9.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.9.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.10.linear_attn.out_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.10.linear_attn.in_proj_qkv": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.10.linear_attn.in_proj_z": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.10.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.10.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.10.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.11.self_attn.q_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.11.self_attn.k_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.11.self_attn.v_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.11.self_attn.o_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.11.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.11.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.11.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.12.linear_attn.out_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.12.linear_attn.in_proj_qkv": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.12.linear_attn.in_proj_z": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.12.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.12.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.12.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.13.linear_attn.out_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.13.linear_attn.in_proj_qkv": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.13.linear_attn.in_proj_z": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.13.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.13.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.13.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.14.linear_attn.out_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.14.linear_attn.in_proj_qkv": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.14.linear_attn.in_proj_z": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.14.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.14.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.14.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.15.self_attn.q_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.15.self_attn.k_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.15.self_attn.v_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.15.self_attn.o_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.15.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.15.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.15.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.16.linear_attn.out_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.16.linear_attn.in_proj_qkv": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.16.linear_attn.in_proj_z": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.16.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.16.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.16.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.17.linear_attn.out_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.17.linear_attn.in_proj_qkv": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.17.linear_attn.in_proj_z": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.17.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.17.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.17.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.18.linear_attn.out_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.18.linear_attn.in_proj_qkv": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.18.linear_attn.in_proj_z": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.18.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.18.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.18.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.19.self_attn.q_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.19.self_attn.k_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.19.self_attn.v_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.19.self_attn.o_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.19.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.19.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.19.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.20.linear_attn.out_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.20.linear_attn.in_proj_qkv": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.20.linear_attn.in_proj_z": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.20.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.20.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.20.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.21.linear_attn.out_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.21.linear_attn.in_proj_qkv": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.21.linear_attn.in_proj_z": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.21.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.21.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.21.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.22.linear_attn.out_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.22.linear_attn.in_proj_qkv": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.22.linear_attn.in_proj_z": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.22.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.22.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.22.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.23.self_attn.q_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.23.self_attn.k_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.23.self_attn.v_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.23.self_attn.o_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.23.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.23.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.23.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.24.linear_attn.out_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.24.linear_attn.in_proj_qkv": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.24.linear_attn.in_proj_z": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.24.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.24.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.24.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.25.linear_attn.out_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.25.linear_attn.in_proj_qkv": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.25.linear_attn.in_proj_z": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.25.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.25.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.25.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.26.linear_attn.out_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.26.linear_attn.in_proj_qkv": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.26.linear_attn.in_proj_z": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.26.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.26.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.26.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.27.self_attn.q_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.27.self_attn.k_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.27.self_attn.v_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.27.self_attn.o_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.27.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.27.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.27.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.28.linear_attn.out_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.28.linear_attn.in_proj_qkv": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.28.linear_attn.in_proj_z": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.28.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.28.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.28.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.29.linear_attn.out_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.29.linear_attn.in_proj_qkv": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.29.linear_attn.in_proj_z": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.29.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.29.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.29.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.30.linear_attn.out_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.30.linear_attn.in_proj_qkv": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.30.linear_attn.in_proj_z": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.30.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.30.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.30.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.31.self_attn.q_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.31.self_attn.k_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.31.self_attn.v_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.31.self_attn.o_proj": {
"quant_algo": "MXFP8",
"group_size": 32
},
"model.language_model.layers.31.mlp.gate_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.31.mlp.up_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"model.language_model.layers.31.mlp.down_proj": {
"quant_algo": "W4A16_NVFP4",
"group_size": 16
},
"lm_head": {
"quant_algo": "MXFP8",
"group_size": 32
}
},
"ignore": [
"mtp*",
"mtp.layers.0*"
],
"quant_algo": "MIXED_PRECISION",
"producer": {
"name": "modelopt",
"version": "0.47.0.dev75+gfbcdc16c2.d20260818"
},
"quant_method": "modelopt"
},
"quantization": {
"bits": 8,
"mode": "mxfp8"
}
}