{
  "source_model": "microsoft/Lens",
  "target_model": "WaveCut/Lens-SDNQ-uint4-static",
  "method": "SDNQ uint4 static",
  "corrected_recipe": true,
  "weights_dtype": "uint4",
  "quantized_matmul_dtype": "int8",
  "group_size": 0,
  "use_quantized_matmul": true,
  "dequantize_fp32": false,
  "modules_to_not_convert_user": [
    ".final_layer",
    "pos_embed",
    ".norm_out",
    ".y_embedder",
    ".context_embedder",
    ".condition_embedder",
    ".x_embedder",
    ".vid_out",
    ".emb_out",
    ".img_in",
    "patch_embed",
    ".time_embed",
    ".t_embedder",
    "multi_modal_projector",
    "patch_emb",
    "norm",
    ".img_out",
    "patch_embedding",
    "lm_head",
    ".proj_out",
    ".vid_in",
    ".txt_in",
    "wte",
    "time_text_embed",
    ".txt_out",
    ".emb_in",
    "*.img_mod.*",
    "*.txt_mod.*"
  ],
  "root_cause_from_turbo_ablation": "Do not quantize transformer modulation linears (*.img_mod.* and *.txt_mod.*); all-linear UINT4 caused periodic grid artifacts and text degradation on Lens-Turbo.",
  "transformer_load_time_s": 3.677,
  "transformer_load_peak_allocated_gb": 8.359,
  "transformer_load_peak_reserved_gb": 8.424,
  "quantization_time_s": 0.313,
  "quantization_peak_allocated_gb": 8.425,
  "quantization_peak_reserved_gb": 8.485,
  "base_transformer_tensor_storage_gb": 16.417,
  "quant_transformer_tensor_storage_gb": 4.301,
  "transformer_storage_reduction_percent": 73.8,
  "base_transformer_repo_files_gb": 16.417,
  "quant_transformer_repo_files_gb": 4.302,
  "base_transformer_dtypes": {
    "FLOAT32": 16416900608
  },
  "quant_transformer_dtypes": {
    "BFLOAT16": 2942501632,
    "UINT8": 1358954496
  },
  "base_transformer_tensors": 1264,
  "quant_transformer_tensors": 2224
}