{ "created_at": "2026-08-08T18:34:34.826502Z", "plan_sha256": "c9d797635006062209fe0ce611c20f6a23e482c91257c5e43a3e73811853bfd7", "records": [ { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.0.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.0.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.0.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.0.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.0.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.0.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.0.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.1.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.1.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.1.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.1.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.1.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.1.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.1.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.10.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.10.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.10.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.10.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.11.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.11.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.11.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.11.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.12.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.12.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.12.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.12.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.13.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.13.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.13.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.13.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.14.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.14.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.14.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.14.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.15.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.15.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.15.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.15.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.16.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.16.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.16.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.16.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.17.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.17.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.17.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.17.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.18.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.18.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.18.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.18.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.19.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.19.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.19.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.19.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.2.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.2.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.2.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.2.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.2.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.2.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.2.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.20.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.20.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.20.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.20.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.21.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.21.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.21.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.21.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.22.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.22.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.22.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.22.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.23.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.23.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.23.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.23.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.24.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.24.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.24.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.24.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.25.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.25.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.25.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.25.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.26.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.26.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.26.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.26.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.27.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.27.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.27.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.27.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.28.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.28.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.28.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.28.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.29.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.29.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.29.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.29.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.3.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.3.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.3.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.3.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.3.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.3.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.3.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.30.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.30.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.30.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.30.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.31.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.31.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.31.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.31.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.32.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.32.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.32.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.32.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.33.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.33.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.33.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.33.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.4.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.4.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.4.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.4.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.4.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.4.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.4.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.5.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.5.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.5.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.5.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.5.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.5.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.5.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "layers.6.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.6.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "layers.6.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "layers.6.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "layers.7.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "layers.7.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "layers.7.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "layers.7.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "layers.8.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "layers.8.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "layers.8.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "layers.8.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "layers.9.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "layers.9.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "layers.9.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "layers.9.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.10.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.10.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.10.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.11.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.11.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.11.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.12.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.12.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.12.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.13.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.13.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.13.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.14.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.14.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.14.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.15.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.15.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.15.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.16.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.16.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.16.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.17.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.17.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.17.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.18.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.18.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.18.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.19.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.19.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.19.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.6.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.6.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.6.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.7.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.7.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.7.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.8.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.8.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.8.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.9.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.9.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.9.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.20.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.20.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.20.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.21.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.21.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.21.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.22.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.22.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.22.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.23.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.23.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.23.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.24.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.24.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.24.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.25.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.25.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.25.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.26.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.26.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.26.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.27.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.27.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.27.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.28.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.28.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.28.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.29.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.29.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.29.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.30.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.30.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.30.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.31.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.31.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.31.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.32.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.32.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.32.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.33.mlp.down_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.33.mlp.gate_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.33.mlp.up_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 8, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "embed_tokens", "note": "mlx-lm affine packing", "success": true } ], "schema_version": "axquant.quantizer-execution.v1" }