{
  "stage": "quantize",
  "source": "Cloudflare/clef-flash@17f0b0ad64efb65d273590632833508766b2aae6",
  "scheme": "NVFP4",
  "targets": "mlp",
  "target_patterns": [
    "re:.*language_model\\.layers\\.\\d+\\.mlp\\.(gate|up|down)_proj$"
  ],
  "ignore": [
    "lm_head",
    "re:.*visual.*",
    "re:.*linear_attn\\.in_proj_a$",
    "re:.*linear_attn\\.in_proj_b$"
  ],
  "quantized_modules": 96,
  "pipeline": "basic",
  "calibration_records": 248,
  "calibration_tokens": 3405837,
  "calibration_max_len": 87189,
  "max_calib_tokens": 131072,
  "ptq_seconds": 556,
  "env": {
    "python": "3.13.15",
    "torch": "2.13.0+cu132",
    "transformers": "5.14.1",
    "llmcompressor": "0.13.0",
    "compressed-tensors": "0.18.0"
  },
  "finished": "2026-10-04T13:06:48"
}