{
  "target": "GPTQ-INT8",
  "status": "complete",
  "smoke_test": false,
  "started_utc": "2026-08-16T16:46:02+00:00",
  "source": "/mnt/c/Users/chunk/OneDrive/Documents/quant3.8/qwen38-cuda-quants/hf-cache/source/Qwen3.8-27B--1d4bf0f2ff60",
  "pinned_source_revision": "1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0",
  "output": "/mnt/c/Users/chunk/OneDrive/Documents/quant3.8/qwen38-cuda-quants/outputs/Qwen3.8-27B-GPTQ-INT8",
  "configuration": {
    "bits": 8,
    "group_size": 128,
    "desc_act": true,
    "lm_head": false,
    "method": "gptq",
    "quant_method": "gptq",
    "format": "gptq",
    "checkpoint_format": "gptq",
    "pack_dtype": "int32",
    "meta": {
      "fallback": {
        "strategy": "rtn",
        "threshold": "0.5%",
        "smooth": null
      },
      "offload_to_disk": false,
      "offload_to_disk_path": null,
      "pack_impl": "cpu",
      "gc_mode": "interval",
      "wait_for_submodule_finalizers": false,
      "auto_forward_data_parallel": true,
      "dense_vram_strategy": "exclusive",
      "dense_vram_strategy_devices": null,
      "moe_vram_strategy": "exclusive",
      "moe_vram_strategy_devices": null,
      "gptaq": null,
      "mse": 0.0,
      "mock_quantization": false,
      "act_group_aware": false,
      "hessian": {
        "chunk_size": null,
        "chunk_bytes": null,
        "staging_dtype": "float32"
      }
    },
    "sym": true,
    "calibration_samples": 128,
    "calibration_sequence_length": 2048,
    "calibration_batch_size": 1,
    "calibration_sort": true,
    "calibration_corpus_sha256": "7ac4e3f0092bd5acfdeaec88f19a8c829458b0716c10ab9e81cda6f8b064b675",
    "estimated_output_bytes_for_disk_gate": 41689594639
  },
  "gptqmodel_quantized": true,
  "finished_utc": "2026-08-16T17:49:22+00:00",
  "elapsed_seconds": 3869.462,
  "resources": {
    "samples": 3542,
    "peak_process_rss_gib": 40.578,
    "peak_system_used_gib": 29.313,
    "peak_gpu_vram_gib": 10.274
  },
  "output_bytes": 31841278679
}