{ "created_at": "2026-08-12T01:08:12.637062Z", "plan_sha256": "77daba154be0d240dc23c32b3ffd19e5c4c24ddb1d6139f9ed7ef29d4d78ebbf", "records": [ { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.0.mlp.experts.down_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.0.mlp.experts.gate_up_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 8, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.0.mlp.router", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.0.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.0.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.0.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.0.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.1.mlp.experts.down_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.1.mlp.experts.gate_up_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 8, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.1.mlp.router", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.1.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.1.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.1.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.1.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.10.mlp.experts.down_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.10.mlp.experts.gate_up_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 8, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.10.mlp.router", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.10.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.10.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.10.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.10.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.11.mlp.experts.down_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.11.mlp.experts.gate_up_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 8, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.11.mlp.router", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.11.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.11.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.11.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.11.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.12.mlp.experts.down_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.12.mlp.experts.gate_up_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 8, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.12.mlp.router", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.12.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.12.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.12.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.12.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.13.mlp.experts.down_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.13.mlp.experts.gate_up_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 8, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.13.mlp.router", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.13.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.13.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.13.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.13.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.14.mlp.experts.down_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.14.mlp.experts.gate_up_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 8, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.14.mlp.router", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.14.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.14.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.14.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.14.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.15.mlp.experts.down_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.15.mlp.experts.gate_up_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 8, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.15.mlp.router", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.15.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.15.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.15.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.15.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.16.mlp.experts.down_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.16.mlp.experts.gate_up_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 8, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.16.mlp.router", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.16.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.16.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.16.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.16.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.17.mlp.experts.down_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.17.mlp.experts.gate_up_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 8, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.17.mlp.router", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.17.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.17.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.17.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.17.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.18.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.18.mlp.experts.down_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.18.mlp.experts.gate_up_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 8, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.18.mlp.router", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.18.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.18.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.18.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.19.mlp.experts.down_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.19.mlp.experts.gate_up_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 8, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.19.mlp.router", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.19.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.19.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.19.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.19.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.2.mlp.experts.down_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.2.mlp.experts.gate_up_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 8, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.2.mlp.router", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.2.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.2.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.2.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.2.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.20.mlp.experts.down_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.20.mlp.experts.gate_up_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 8, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.20.mlp.router", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.20.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.20.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.20.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.20.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.21.mlp.experts.down_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.21.mlp.experts.gate_up_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 8, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.21.mlp.router", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.21.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.21.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.21.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.21.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.22.mlp.experts.down_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.22.mlp.experts.gate_up_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 8, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.22.mlp.router", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.22.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.22.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.22.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.22.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.23.mlp.experts.down_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.23.mlp.experts.gate_up_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 8, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.23.mlp.router", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.23.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.23.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.23.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.23.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.3.mlp.experts.down_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.3.mlp.experts.gate_up_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 8, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.3.mlp.router", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.3.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.3.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.3.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.3.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.4.mlp.experts.down_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.4.mlp.experts.gate_up_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 8, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.4.mlp.router", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.4.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.4.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.4.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.4.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.5.mlp.experts.down_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.5.mlp.experts.gate_up_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 8, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.5.mlp.router", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.5.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.5.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.5.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.5.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 8, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.6.mlp.router", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.6.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.6.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.6.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.6.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 8, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.embed_tokens", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.6.mlp.experts.down_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.6.mlp.experts.gate_up_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.7.mlp.experts.down_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.7.mlp.experts.gate_up_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 8, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.7.mlp.router", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.7.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.7.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.7.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 8, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.7.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.8.mlp.experts.down_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.8.mlp.experts.gate_up_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 8, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.8.mlp.router", "note": "mlx-lm affine packing", "success": true }, { "bits": 8, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.8.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.8.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.8.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 8, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.8.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.9.mlp.experts.down_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.9.mlp.experts.gate_up_proj_blocks", "note": "mlx-lm affine packing", "success": true }, { "bits": 8, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.9.mlp.router", "note": "mlx-lm affine packing", "success": true }, { "bits": 8, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.9.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.9.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 6, "fallback": false, "group_size": 32, "metadata": {}, "method": "affine", "module_path": "model.layers.9.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 8, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "model.layers.9.self_attn.v_proj", "note": "mlx-lm affine packing", "success": true } ], "schema_version": "axquant.quantizer-execution.v1" }