{ "created_at": "2026-08-08T18:33:57.675920Z", "plan_sha256": "577c696c74285a59d024db2c2261382776bd126ee62a1396a60430ef5b412427", "records": [ { "bits": 8, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "embed_tokens", "note": "mlx-lm affine packing", "success": true }, { "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.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.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.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.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.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.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.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.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.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.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.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.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.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.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.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": 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.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": 64, "metadata": {}, "method": "affine", "module_path": "layers.6.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.6.self_attn.v_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.7.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.7.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.7.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.7.self_attn.v_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.8.self_attn.k_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.8.self_attn.o_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.8.self_attn.q_proj", "note": "mlx-lm affine packing", "success": true }, { "bits": 4, "fallback": false, "group_size": 64, "metadata": {}, "method": "affine", "module_path": "layers.8.self_attn.v_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": 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 } ], "schema_version": "axquant.quantizer-execution.v1" }