AX-DeepSeek-OCR-2-MLX-AXQ-4bit / axquant_quantizer_execution.json
AutomatosX's picture
AXQ 4-bit development pack from DeepSeek-OCR-2@aaa02f3811945a91062062994c5c4a3f4c0af2b0
bf87c5d verified
Raw
History Blame Contribute Delete
31.5 kB
{
"created_at": "2026-08-13T23:52:26.819280Z",
"plan_sha256": "94b91b02df29386eeca990831e21f6adc9d93fc9802807b4873970a9fb75ca85",
"records": [
{
"bits": 8,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.embed_tokens",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.0.mlp.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.0.mlp.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.0.mlp.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.0.self_attn.k_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.0.self_attn.o_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.0.self_attn.q_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.0.self_attn.v_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.1.mlp.shared_experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.1.mlp.shared_experts.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.1.mlp.shared_experts.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.1.mlp.switch_mlp.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.1.mlp.switch_mlp.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.1.mlp.switch_mlp.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.1.self_attn.k_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.1.self_attn.o_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.1.self_attn.q_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.1.self_attn.v_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.2.mlp.shared_experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.2.mlp.shared_experts.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.2.mlp.shared_experts.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.2.mlp.switch_mlp.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.2.mlp.switch_mlp.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.2.mlp.switch_mlp.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.2.self_attn.k_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.2.self_attn.o_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.2.self_attn.q_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.2.self_attn.v_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.3.mlp.shared_experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.3.mlp.shared_experts.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.3.mlp.shared_experts.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.3.mlp.switch_mlp.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.3.mlp.switch_mlp.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.3.mlp.switch_mlp.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.3.self_attn.k_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.3.self_attn.o_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.3.self_attn.q_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.3.self_attn.v_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.4.mlp.shared_experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.4.mlp.shared_experts.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.4.mlp.shared_experts.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.4.mlp.switch_mlp.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.4.mlp.switch_mlp.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.4.mlp.switch_mlp.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.4.self_attn.k_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.4.self_attn.o_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.4.self_attn.q_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.4.self_attn.v_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.5.mlp.shared_experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.5.mlp.shared_experts.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.5.mlp.shared_experts.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.5.mlp.switch_mlp.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.5.mlp.switch_mlp.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.5.mlp.switch_mlp.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.5.self_attn.k_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.5.self_attn.o_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.5.self_attn.q_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.5.self_attn.v_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.6.mlp.shared_experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.6.mlp.shared_experts.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.6.mlp.shared_experts.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.6.mlp.switch_mlp.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.6.mlp.switch_mlp.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.6.mlp.switch_mlp.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.6.self_attn.k_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.6.self_attn.o_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.6.self_attn.q_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.6.self_attn.v_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.7.mlp.shared_experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.7.mlp.shared_experts.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.7.mlp.shared_experts.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.7.mlp.switch_mlp.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.7.mlp.switch_mlp.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.7.mlp.switch_mlp.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.7.self_attn.k_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.7.self_attn.o_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.7.self_attn.q_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.7.self_attn.v_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.8.mlp.shared_experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.8.mlp.shared_experts.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.8.mlp.shared_experts.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.8.mlp.switch_mlp.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.8.mlp.switch_mlp.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.8.mlp.switch_mlp.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.8.self_attn.k_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.8.self_attn.o_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.8.self_attn.q_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.8.self_attn.v_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.9.mlp.switch_mlp.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.9.mlp.switch_mlp.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.9.self_attn.k_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.9.self_attn.o_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.9.self_attn.q_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.9.self_attn.v_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.10.mlp.shared_experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.10.mlp.shared_experts.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.10.mlp.shared_experts.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.10.mlp.switch_mlp.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.10.mlp.switch_mlp.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.10.mlp.switch_mlp.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.10.self_attn.k_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.10.self_attn.o_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.10.self_attn.q_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.10.self_attn.v_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.11.mlp.shared_experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.11.mlp.shared_experts.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.11.mlp.shared_experts.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.11.mlp.switch_mlp.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.11.mlp.switch_mlp.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.11.mlp.switch_mlp.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.11.self_attn.k_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.11.self_attn.o_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.11.self_attn.q_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.11.self_attn.v_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.9.mlp.shared_experts.down_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.9.mlp.shared_experts.gate_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.9.mlp.shared_experts.up_proj",
"note": "mlx-vlm affine packing",
"success": true
},
{
"bits": 4,
"fallback": false,
"group_size": 64,
"metadata": {},
"method": "affine",
"module_path": "language_model.model.layers.9.mlp.switch_mlp.down_proj",
"note": "mlx-vlm affine packing",
"success": true
}
],
"schema_version": "axquant.quantizer-execution.v1"
}