{
  "method": "optiq_mixed_precision",
  "base_model": "ornith-ai/Ornith-1.5-9B-MLX",
  "default_bits": 4,
  "group_size": 64,
  "bit_widths_used": [
    4,
    8
  ],
  "layers_per_bit_width": {
    "4": 116,
    "8": 134
  },
  "n_quantized_layers": 250,
  "per_layer": {
    "language_model.model.embed_tokens": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.0.linear_attn.in_proj_qkv": {
      "bits": 8,
      "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_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.0.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.0.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.0.mlp.gate_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.0.mlp.down_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.0.mlp.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.1.linear_attn.in_proj_qkv": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.1.linear_attn.in_proj_z": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.1.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.1.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.1.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.1.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.1.mlp.down_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.1.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.2.linear_attn.in_proj_qkv": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.2.linear_attn.in_proj_z": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.2.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.2.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.2.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.2.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.2.mlp.down_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.2.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.3.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.3.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.3.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.3.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.3.mlp.gate_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.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.4.linear_attn.in_proj_qkv": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.4.linear_attn.in_proj_z": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.4.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.4.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.4.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.4.mlp.gate_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.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.5.linear_attn.in_proj_qkv": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.5.linear_attn.in_proj_z": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.5.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.5.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.5.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.5.mlp.gate_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.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.6.linear_attn.in_proj_qkv": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.6.linear_attn.in_proj_z": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.6.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.6.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.6.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.6.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.6.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.6.mlp.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.7.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.7.self_attn.k_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.o_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.7.mlp.gate_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.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.8.linear_attn.in_proj_qkv": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.8.linear_attn.in_proj_z": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.8.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.8.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.8.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.8.mlp.gate_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.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.9.linear_attn.in_proj_qkv": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.9.linear_attn.in_proj_z": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.9.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.9.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.9.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.9.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.9.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.9.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.10.linear_attn.in_proj_qkv": {
      "bits": 8,
      "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_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.10.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.10.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.10.mlp.gate_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.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.11.self_attn.q_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.11.self_attn.k_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.o_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.11.mlp.gate_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.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.12.linear_attn.in_proj_qkv": {
      "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_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.12.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.12.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.12.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.12.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.12.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.13.linear_attn.in_proj_qkv": {
      "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_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.13.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.13.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.13.mlp.gate_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.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.14.linear_attn.in_proj_qkv": {
      "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_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.14.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.14.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.14.mlp.gate_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.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.15.self_attn.q_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.15.self_attn.k_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.o_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.15.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.15.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.15.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.16.linear_attn.in_proj_qkv": {
      "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_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.16.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.16.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.16.mlp.gate_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.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.17.linear_attn.in_proj_qkv": {
      "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_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.17.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.17.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.17.mlp.gate_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.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.18.linear_attn.in_proj_qkv": {
      "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_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.18.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.18.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.18.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.18.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.18.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.19.self_attn.q_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.19.self_attn.k_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.19.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.19.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.19.mlp.gate_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.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.20.linear_attn.in_proj_qkv": {
      "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_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.20.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.20.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.20.mlp.gate_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.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.21.linear_attn.in_proj_qkv": {
      "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_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.21.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.21.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.21.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.21.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.21.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.22.linear_attn.in_proj_qkv": {
      "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_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.22.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.22.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.22.mlp.gate_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.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.23.self_attn.q_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.23.self_attn.k_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.23.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.23.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.23.mlp.gate_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.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.24.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.24.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.24.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.24.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.24.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.24.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.24.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.24.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.25.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.25.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.25.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.25.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.25.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.25.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.25.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.25.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.26.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.26.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.26.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.26.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.26.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.26.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.26.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.26.mlp.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.27.self_attn.q_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.27.self_attn.k_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.27.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.27.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.27.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.27.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.27.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.28.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.28.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.28.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.28.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.28.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.28.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.28.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.28.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.29.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.29.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.29.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.29.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.29.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.29.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.29.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.29.mlp.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.30.linear_attn.in_proj_qkv": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.30.linear_attn.in_proj_z": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.30.linear_attn.in_proj_b": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.30.linear_attn.in_proj_a": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.30.linear_attn.out_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.30.mlp.gate_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.30.mlp.down_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.30.mlp.up_proj": {
      "bits": 4,
      "group_size": 64
    },
    "language_model.model.layers.31.self_attn.q_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.31.self_attn.k_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.31.self_attn.v_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.31.self_attn.o_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.31.mlp.gate_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.31.mlp.down_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.model.layers.31.mlp.up_proj": {
      "bits": 8,
      "group_size": 64
    },
    "language_model.lm_head": {
      "bits": 8,
      "group_size": 64
    }
  },
  "recipe_reused_from": "mlx-community/Ornith-1.0-9B-OptiQ-4bit",
  "recipe_note": "Per-layer bit allocation reused from the base model's OptiQ quant rather than re-measured. A same-architecture variant has the same per-layer sensitivity structure, so the sweep would reproduce this allocation."
}