ONNX Model Zoo

soiji/Llama-3.2-1B-Instruct_Mobilequant_w4a16_PCQ

By soiji · ↓ 7 · ♥ 0 · Updated 2026-02-23

What's in this repo

This page lists the files in soiji/Llama-3.2-1B-Instruct_Mobilequant_w4a16_PCQ, including model_cl4096.onnx.

  • 1 ONNX models (.onnx files)
  • 211 files, including 115 .weight, 5 .json, 2 .pt, 1 .md, 1 .0_mlp_down_proj_weight_constant_attr__value, 1 .0_mlp_gate_proj_weight_constant_1_attr__value
  • Last updated 2026-02-23

ONNX files

File Size Download
model_cl4096.onnx — Download

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

README

It brokes due to imcompatibility between spinquant and mobilequant. Do not use it

Model info

onnx llama license:mit region:us
↓ 7 ♥ 0

Created: 2026-02-02

Updated: 2026-02-23

View on Hugging Face

Files (211)

.gitattributes
README.md
_model_lm_head_weight_Constant_1_attr__value
_model_lm_head_weight_Constant_attr__value
_model_model_layers.0_mlp_down_proj_weight_Constant_attr__value
_model_model_layers.0_mlp_gate_proj_weight_Constant_1_attr__value
_model_model_layers.0_mlp_gate_proj_weight_Constant_attr__value
_model_model_layers.0_mlp_up_proj_weight_Constant_attr__value
_model_model_layers.0_self_attn_o_proj_weight_Constant_attr__value
_model_model_layers.0_self_attn_q_proj_weight_Constant_1_attr__value
_model_model_layers.0_self_attn_q_proj_weight_Constant_attr__value
_model_model_layers.10_mlp_down_proj_weight_Constant_attr__value
_model_model_layers.10_mlp_gate_proj_weight_Constant_attr__value
_model_model_layers.10_mlp_up_proj_weight_Constant_attr__value
_model_model_layers.10_self_attn_o_proj_weight_Constant_attr__value
_model_model_layers.10_self_attn_q_proj_weight_Constant_attr__value
_model_model_layers.11_mlp_down_proj_weight_Constant_attr__value
_model_model_layers.11_mlp_gate_proj_weight_Constant_attr__value
_model_model_layers.11_mlp_up_proj_weight_Constant_attr__value
_model_model_layers.11_self_attn_o_proj_weight_Constant_attr__value
_model_model_layers.11_self_attn_q_proj_weight_Constant_attr__value
_model_model_layers.12_mlp_down_proj_weight_Constant_attr__value
_model_model_layers.12_mlp_gate_proj_weight_Constant_attr__value
_model_model_layers.12_mlp_up_proj_weight_Constant_attr__value
_model_model_layers.12_self_attn_o_proj_weight_Constant_attr__value
_model_model_layers.12_self_attn_q_proj_weight_Constant_attr__value
_model_model_layers.13_mlp_down_proj_weight_Constant_attr__value
_model_model_layers.13_mlp_gate_proj_weight_Constant_attr__value
_model_model_layers.13_mlp_up_proj_weight_Constant_attr__value
_model_model_layers.13_self_attn_o_proj_weight_Constant_attr__value
_model_model_layers.13_self_attn_q_proj_weight_Constant_attr__value
_model_model_layers.14_mlp_down_proj_weight_Constant_attr__value
_model_model_layers.14_mlp_gate_proj_weight_Constant_attr__value
_model_model_layers.14_mlp_up_proj_weight_Constant_attr__value
_model_model_layers.14_self_attn_o_proj_weight_Constant_attr__value
_model_model_layers.14_self_attn_q_proj_weight_Constant_attr__value
_model_model_layers.15_mlp_down_proj_weight_Constant_attr__value
_model_model_layers.15_mlp_gate_proj_weight_Constant_attr__value
_model_model_layers.15_mlp_up_proj_weight_Constant_attr__value
_model_model_layers.15_self_attn_o_proj_weight_Constant_attr__value
_model_model_layers.15_self_attn_q_proj_weight_Constant_attr__value
_model_model_layers.1_mlp_down_proj_weight_Constant_attr__value
_model_model_layers.1_mlp_gate_proj_weight_Constant_attr__value
_model_model_layers.1_mlp_up_proj_weight_Constant_attr__value
_model_model_layers.1_self_attn_o_proj_weight_Constant_attr__value
_model_model_layers.1_self_attn_q_proj_weight_Constant_attr__value
_model_model_layers.2_mlp_down_proj_weight_Constant_attr__value
_model_model_layers.2_mlp_gate_proj_weight_Constant_attr__value
_model_model_layers.2_mlp_up_proj_weight_Constant_attr__value
_model_model_layers.2_self_attn_o_proj_weight_Constant_attr__value
_model_model_layers.2_self_attn_q_proj_weight_Constant_attr__value
_model_model_layers.3_mlp_down_proj_weight_Constant_attr__value
_model_model_layers.3_mlp_gate_proj_weight_Constant_attr__value
_model_model_layers.3_mlp_up_proj_weight_Constant_attr__value
_model_model_layers.3_self_attn_o_proj_weight_Constant_attr__value
_model_model_layers.3_self_attn_q_proj_weight_Constant_attr__value
_model_model_layers.4_mlp_down_proj_weight_Constant_attr__value
_model_model_layers.4_mlp_gate_proj_weight_Constant_attr__value
_model_model_layers.4_mlp_up_proj_weight_Constant_attr__value
_model_model_layers.4_self_attn_o_proj_weight_Constant_attr__value
_model_model_layers.4_self_attn_q_proj_weight_Constant_attr__value
_model_model_layers.5_mlp_down_proj_weight_Constant_attr__value
_model_model_layers.5_mlp_gate_proj_weight_Constant_attr__value
_model_model_layers.5_mlp_up_proj_weight_Constant_attr__value
_model_model_layers.5_self_attn_o_proj_weight_Constant_attr__value
_model_model_layers.5_self_attn_q_proj_weight_Constant_attr__value
_model_model_layers.6_mlp_down_proj_weight_Constant_attr__value
_model_model_layers.6_mlp_gate_proj_weight_Constant_attr__value
_model_model_layers.6_mlp_up_proj_weight_Constant_attr__value
_model_model_layers.6_self_attn_o_proj_weight_Constant_attr__value
_model_model_layers.6_self_attn_q_proj_weight_Constant_attr__value
_model_model_layers.7_mlp_down_proj_weight_Constant_attr__value
_model_model_layers.7_mlp_gate_proj_weight_Constant_attr__value
_model_model_layers.7_mlp_up_proj_weight_Constant_attr__value
_model_model_layers.7_self_attn_o_proj_weight_Constant_attr__value
_model_model_layers.7_self_attn_q_proj_weight_Constant_attr__value
_model_model_layers.8_mlp_down_proj_weight_Constant_attr__value
_model_model_layers.8_mlp_gate_proj_weight_Constant_attr__value
_model_model_layers.8_mlp_up_proj_weight_Constant_attr__value
_model_model_layers.8_self_attn_o_proj_weight_Constant_attr__value
_model_model_layers.8_self_attn_q_proj_weight_Constant_attr__value
_model_model_layers.9_mlp_down_proj_weight_Constant_attr__value
_model_model_layers.9_mlp_gate_proj_weight_Constant_attr__value
_model_model_layers.9_mlp_up_proj_weight_Constant_attr__value
_model_model_layers.9_self_attn_o_proj_weight_Constant_attr__value
_model_model_layers.9_self_attn_q_proj_weight_Constant_attr__value
chat_template.jinja
config.json
manifest.json
model.lm_head.weight
model.model.embed_tokens.weight
model.model.layers.0.input_layernorm.weight
model.model.layers.0.mlp.down_proj.weight
model.model.layers.0.mlp.gate_proj.weight
model.model.layers.0.mlp.up_proj.weight
model.model.layers.0.self_attn.k_proj.weight
model.model.layers.0.self_attn.o_proj.weight
model.model.layers.0.self_attn.q_proj.weight
model.model.layers.0.self_attn.v_proj.weight
model.model.layers.1.mlp.down_proj.weight
model.model.layers.1.mlp.gate_proj.weight
model.model.layers.1.mlp.up_proj.weight
model.model.layers.1.self_attn.k_proj.weight
model.model.layers.1.self_attn.o_proj.weight
model.model.layers.1.self_attn.q_proj.weight
model.model.layers.1.self_attn.v_proj.weight
model.model.layers.10.mlp.down_proj.weight
model.model.layers.10.mlp.gate_proj.weight
model.model.layers.10.mlp.up_proj.weight
model.model.layers.10.self_attn.k_proj.weight
model.model.layers.10.self_attn.o_proj.weight
model.model.layers.10.self_attn.q_proj.weight
model.model.layers.10.self_attn.v_proj.weight
model.model.layers.11.mlp.down_proj.weight
model.model.layers.11.mlp.gate_proj.weight
model.model.layers.11.mlp.up_proj.weight
model.model.layers.11.self_attn.k_proj.weight
model.model.layers.11.self_attn.o_proj.weight
model.model.layers.11.self_attn.q_proj.weight
model.model.layers.11.self_attn.v_proj.weight
model.model.layers.12.mlp.down_proj.weight
model.model.layers.12.mlp.gate_proj.weight
model.model.layers.12.mlp.up_proj.weight
model.model.layers.12.self_attn.k_proj.weight
model.model.layers.12.self_attn.o_proj.weight
model.model.layers.12.self_attn.q_proj.weight
model.model.layers.12.self_attn.v_proj.weight
model.model.layers.13.mlp.down_proj.weight
model.model.layers.13.mlp.gate_proj.weight
model.model.layers.13.mlp.up_proj.weight
model.model.layers.13.self_attn.k_proj.weight
model.model.layers.13.self_attn.o_proj.weight
model.model.layers.13.self_attn.q_proj.weight
model.model.layers.13.self_attn.v_proj.weight
model.model.layers.14.mlp.down_proj.weight
model.model.layers.14.mlp.gate_proj.weight
model.model.layers.14.mlp.up_proj.weight
model.model.layers.14.self_attn.k_proj.weight
model.model.layers.14.self_attn.o_proj.weight
model.model.layers.14.self_attn.q_proj.weight
model.model.layers.14.self_attn.v_proj.weight
model.model.layers.15.mlp.down_proj.weight
model.model.layers.15.mlp.gate_proj.weight
model.model.layers.15.mlp.up_proj.weight
model.model.layers.15.self_attn.k_proj.weight
model.model.layers.15.self_attn.o_proj.weight
model.model.layers.15.self_attn.q_proj.weight
model.model.layers.15.self_attn.v_proj.weight
model.model.layers.2.mlp.down_proj.weight
model.model.layers.2.mlp.gate_proj.weight
model.model.layers.2.mlp.up_proj.weight
model.model.layers.2.self_attn.k_proj.weight
model.model.layers.2.self_attn.o_proj.weight
model.model.layers.2.self_attn.q_proj.weight
model.model.layers.2.self_attn.v_proj.weight
model.model.layers.3.mlp.down_proj.weight
model.model.layers.3.mlp.gate_proj.weight
model.model.layers.3.mlp.up_proj.weight
model.model.layers.3.self_attn.k_proj.weight
model.model.layers.3.self_attn.o_proj.weight
model.model.layers.3.self_attn.q_proj.weight
model.model.layers.3.self_attn.v_proj.weight
model.model.layers.4.mlp.down_proj.weight
model.model.layers.4.mlp.gate_proj.weight
model.model.layers.4.mlp.up_proj.weight
model.model.layers.4.self_attn.k_proj.weight
model.model.layers.4.self_attn.o_proj.weight
model.model.layers.4.self_attn.q_proj.weight
model.model.layers.4.self_attn.v_proj.weight
model.model.layers.5.mlp.down_proj.weight
model.model.layers.5.mlp.gate_proj.weight
model.model.layers.5.mlp.up_proj.weight
model.model.layers.5.self_attn.k_proj.weight
model.model.layers.5.self_attn.o_proj.weight
model.model.layers.5.self_attn.q_proj.weight
model.model.layers.5.self_attn.v_proj.weight
model.model.layers.6.mlp.down_proj.weight
model.model.layers.6.mlp.gate_proj.weight
model.model.layers.6.mlp.up_proj.weight
model.model.layers.6.self_attn.k_proj.weight
model.model.layers.6.self_attn.o_proj.weight
model.model.layers.6.self_attn.q_proj.weight
model.model.layers.6.self_attn.v_proj.weight
model.model.layers.7.mlp.down_proj.weight
model.model.layers.7.mlp.gate_proj.weight
model.model.layers.7.mlp.up_proj.weight
model.model.layers.7.self_attn.k_proj.weight
model.model.layers.7.self_attn.o_proj.weight
model.model.layers.7.self_attn.q_proj.weight
model.model.layers.7.self_attn.v_proj.weight
model.model.layers.8.mlp.down_proj.weight
model.model.layers.8.mlp.gate_proj.weight
model.model.layers.8.mlp.up_proj.weight
model.model.layers.8.self_attn.k_proj.weight
model.model.layers.8.self_attn.o_proj.weight
model.model.layers.8.self_attn.q_proj.weight
model.model.layers.8.self_attn.v_proj.weight
model.model.layers.9.mlp.down_proj.weight
model.model.layers.9.mlp.gate_proj.weight
model.model.layers.9.mlp.up_proj.weight
model.model.layers.9.self_attn.k_proj.weight
model.model.layers.9.self_attn.o_proj.weight
model.model.layers.9.self_attn.q_proj.weight
model.model.layers.9.self_attn.v_proj.weight
model_cl4096.encodings
model_cl4096.onnx ONNX
model_cls4096.pt
model_cls4096_quantizer.pt
special_tokens_map.json
tokenizer.json
tokenizer_config.json

Related models