| { |
| "method": "optiq_mixed_precision", |
| "base_model": "Qwen/Qwen3.5-0.8B", |
| "reference": "bf16", |
| "target_bpw": 5.0, |
| "achieved_bpw": 5.5930462267878305, |
| "n_high_bits": 56, |
| "n_low_bits": 130, |
| "threshold": 0.0, |
| "per_layer": { |
| "language_model.model.layers.23.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.23.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.23.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.23.self_attn.o_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.23.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.23.self_attn.k_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.23.self_attn.q_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.22.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.22.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.22.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.22.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.22.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.22.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.22.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.22.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.21.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.21.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.21.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.21.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.21.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.21.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.21.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.21.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.20.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.20.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.20.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.20.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.20.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.20.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.20.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.20.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.19.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.19.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.19.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.19.self_attn.o_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.19.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.19.self_attn.k_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.19.self_attn.q_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.18.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.18.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.18.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.18.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.18.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.18.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.18.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.18.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.17.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.17.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.17.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.17.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.17.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.17.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.17.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.17.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.16.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.16.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.16.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.16.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.16.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.16.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.16.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.16.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.15.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.15.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.15.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.15.self_attn.o_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.15.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.15.self_attn.k_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.15.self_attn.q_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.14.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.14.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.14.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.14.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.14.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.14.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.14.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.14.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.13.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.13.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.13.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.13.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.13.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.13.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.13.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.13.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.12.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.12.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.12.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.12.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.12.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.12.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.12.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.12.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.11.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.11.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.11.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.11.self_attn.o_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.11.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.11.self_attn.k_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.11.self_attn.q_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.10.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.10.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.10.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.10.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.10.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.10.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.10.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.10.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.9.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.9.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.9.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.9.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.9.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.9.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.9.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.9.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.8.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.8.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.8.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.8.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.8.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.8.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.8.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.8.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.7.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.7.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.7.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.7.self_attn.o_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.7.self_attn.v_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.7.self_attn.k_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.7.self_attn.q_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.6.mlp.up_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.6.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.6.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.6.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.6.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.6.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.6.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.6.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.5.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.5.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.5.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.5.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.5.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.5.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.5.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.5.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.4.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.4.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.4.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.4.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.4.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.4.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.4.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.4.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.3.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.3.mlp.down_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.3.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.3.self_attn.o_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.3.self_attn.v_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.3.self_attn.k_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.3.self_attn.q_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.2.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.2.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.2.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.2.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.2.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.2.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.2.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.2.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.1.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.1.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.1.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.1.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.1.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.1.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.1.linear_attn.in_proj_z": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.1.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.0.mlp.up_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.0.mlp.down_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.0.mlp.gate_proj": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.0.linear_attn.out_proj": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.0.linear_attn.in_proj_a": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.0.linear_attn.in_proj_b": { |
| "bits": 4, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.0.linear_attn.in_proj_z": { |
| "bits": 8, |
| "group_size": 64 |
| }, |
| "language_model.model.layers.0.linear_attn.in_proj_qkv": { |
| "bits": 8, |
| "group_size": 64 |
| } |
| } |
| } |
