AX-gemma-4-26b-a4b-MLX-AXQ-4bit-MTP / axquant_quantizer_execution.json
AutomatosX's picture
Rebuild Gemma MTP pack for MLX-VLM and oMLX compatibility
1327f08 verified
Raw
History Blame Contribute Delete
76.7 kB
{
"created_at": "2026-08-30T14:15:10.446736Z",
"plan_sha256": "b7f9acf2a737308ebaa8a5182d7f27a626efa27d8590c1e887e5414255925a73",
"records": [
{
"bits": 8,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.embed_tokens",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.0.experts.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.0.experts.gate_up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.0.mlp.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.0.mlp.gate_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.0.mlp.up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.0.router.proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.0.self_attn.k_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.0.self_attn.o_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.0.self_attn.q_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.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": "model.language_model.layers.1.experts.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.experts.gate_up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.mlp.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.mlp.gate_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.mlp.up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.router.proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.self_attn.k_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.self_attn.o_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.1.self_attn.q_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.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": "model.language_model.layers.10.experts.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.10.experts.gate_up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.10.mlp.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.10.mlp.gate_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.10.mlp.up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.10.router.proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.10.self_attn.k_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.10.self_attn.o_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.10.self_attn.q_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.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": "model.language_model.layers.11.experts.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.11.experts.gate_up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.11.self_attn.k_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.11.self_attn.o_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.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": "model.language_model.layers.12.experts.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.12.experts.gate_up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.12.mlp.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.12.mlp.gate_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.12.mlp.up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.12.router.proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.12.self_attn.k_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.12.self_attn.o_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.12.self_attn.q_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.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": "model.language_model.layers.13.experts.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.13.experts.gate_up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.13.mlp.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.13.mlp.gate_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.13.mlp.up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.13.router.proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.13.self_attn.k_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.13.self_attn.o_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.13.self_attn.q_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.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": "model.language_model.layers.14.experts.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.14.experts.gate_up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.14.mlp.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.14.mlp.gate_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.14.mlp.up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.14.router.proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.14.self_attn.k_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.14.self_attn.o_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.14.self_attn.q_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.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": "model.language_model.layers.15.experts.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.15.experts.gate_up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.15.mlp.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.15.mlp.gate_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.15.mlp.up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.15.router.proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.15.self_attn.k_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.15.self_attn.o_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.15.self_attn.q_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.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": "model.language_model.layers.16.experts.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.16.experts.gate_up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.16.mlp.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.16.mlp.gate_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.16.mlp.up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.16.router.proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.16.self_attn.k_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.16.self_attn.o_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.16.self_attn.q_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.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": "model.language_model.layers.17.experts.gate_up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.17.self_attn.k_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.17.self_attn.o_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.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": "model.language_model.layers.18.experts.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.18.experts.gate_up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.18.mlp.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.18.mlp.gate_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.18.mlp.up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.18.router.proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.18.self_attn.k_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_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.language_model.layers.18.self_attn.q_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.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": "model.language_model.layers.19.experts.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.19.experts.gate_up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.19.mlp.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.19.mlp.gate_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.19.mlp.up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.19.router.proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.19.self_attn.k_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.19.self_attn.o_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.19.self_attn.q_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.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": "model.language_model.layers.2.experts.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.2.experts.gate_up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.2.mlp.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.2.mlp.gate_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.2.mlp.up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.2.router.proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.2.self_attn.k_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.2.self_attn.o_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.2.self_attn.q_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.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": "model.language_model.layers.20.experts.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.20.experts.gate_up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.20.mlp.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.20.mlp.gate_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.20.mlp.up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.20.router.proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.20.self_attn.k_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.20.self_attn.o_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.20.self_attn.q_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.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": "model.language_model.layers.21.experts.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.21.experts.gate_up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.21.mlp.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.21.mlp.gate_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.21.mlp.up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.21.router.proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.21.self_attn.k_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.21.self_attn.o_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.21.self_attn.q_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.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": "model.language_model.layers.22.experts.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.22.experts.gate_up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.22.mlp.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.22.mlp.gate_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.22.mlp.up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.22.router.proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.22.self_attn.k_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.22.self_attn.o_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.22.self_attn.q_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.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": "model.language_model.layers.23.experts.gate_up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.23.self_attn.k_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.23.self_attn.o_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.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": "model.language_model.layers.24.experts.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.24.experts.gate_up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.24.mlp.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.24.mlp.gate_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.24.mlp.up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.24.router.proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.24.self_attn.k_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.24.self_attn.o_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.24.self_attn.q_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.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": "model.language_model.layers.25.experts.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.25.experts.gate_up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.25.mlp.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.25.mlp.gate_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.25.mlp.up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.25.router.proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.25.self_attn.k_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.25.self_attn.o_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.25.self_attn.q_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.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": "model.language_model.layers.26.experts.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.26.experts.gate_up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.26.mlp.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.26.mlp.gate_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.26.mlp.up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.26.router.proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.26.self_attn.k_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.26.self_attn.o_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.26.self_attn.q_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.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": "model.language_model.layers.27.experts.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.27.experts.gate_up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.27.mlp.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.27.mlp.gate_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.27.mlp.up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.27.router.proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.27.self_attn.k_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.27.self_attn.o_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.27.self_attn.q_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.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": "model.language_model.layers.28.experts.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.28.experts.gate_up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.28.mlp.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.28.mlp.gate_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.28.mlp.up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.28.router.proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.28.self_attn.k_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.28.self_attn.o_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.28.self_attn.q_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.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": "model.language_model.layers.29.experts.gate_up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.29.self_attn.k_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.29.self_attn.o_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.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": "model.language_model.layers.3.experts.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.3.experts.gate_up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.3.mlp.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.3.mlp.gate_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.3.mlp.up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.3.router.proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.3.self_attn.k_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.3.self_attn.o_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.3.self_attn.q_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.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": "model.language_model.layers.4.experts.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.4.experts.gate_up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.4.mlp.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.4.mlp.gate_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.4.mlp.up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.4.router.proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.4.self_attn.k_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.4.self_attn.o_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.4.self_attn.q_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.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": "model.language_model.layers.5.experts.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.5.experts.gate_up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.5.self_attn.k_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.5.self_attn.o_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.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": "model.language_model.layers.6.experts.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.6.experts.gate_up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.6.mlp.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.6.mlp.gate_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.6.mlp.up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.6.router.proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.6.self_attn.k_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.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": "model.language_model.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": "model.language_model.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": "model.language_model.layers.7.experts.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.7.experts.gate_up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.7.mlp.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.7.mlp.gate_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.7.mlp.up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.7.router.proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.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": "model.language_model.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": "model.language_model.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": "model.language_model.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": "model.language_model.layers.8.experts.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.8.experts.gate_up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.8.mlp.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.8.mlp.gate_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.8.mlp.up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.8.router.proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.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": "model.language_model.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": "model.language_model.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": "model.language_model.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": "model.language_model.layers.9.experts.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.9.experts.gate_up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.9.mlp.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.9.mlp.gate_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.9.mlp.up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.9.router.proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.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": "model.language_model.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": "model.language_model.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": "model.language_model.layers.9.self_attn.v_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.11.mlp.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.11.mlp.gate_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.11.mlp.up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.11.router.proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.17.experts.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.17.mlp.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.17.mlp.gate_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.17.mlp.up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.17.router.proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.23.experts.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.23.mlp.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.23.mlp.gate_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.23.mlp.up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.23.router.proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.29.experts.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.29.mlp.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.29.mlp.gate_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.29.mlp.up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.29.router.proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.5.mlp.down_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.5.mlp.gate_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.5.mlp.up_proj",
"note": "mlx-lm affine packing",
"success": true
},
{
"bits": 8,
"fallback": false,
"group_size": 32,
"metadata": {},
"method": "affine",
"module_path": "model.language_model.layers.5.router.proj",
"note": "mlx-lm affine packing",
"success": true
}
],
"schema_version": "axquant.quantizer-execution.v1"
}