{
  "schemaVersion": 1,
  "createdUtc": "2026-08-26T12:42:28.482622+00:00",
  "experiment": "MQ-IQ2_M_1-Generic",
  "status": "complete",
  "models": {
    "native": {
      "path": "<REPO_ROOT>/Qwen3.8-27B-Quark-AWQ-MXFP4-native.gguf",
      "bytes": 18892854880,
      "decimalGB": 18.89285488,
      "GiB": 17.595342248678207,
      "sha256": "1a37c48570811215fa1a9d2a493211293ca375d17287771e85d28642946e88fc"
    },
    "candidate": {
      "path": "<REPO_ROOT>/Qwen3.8-27B-Quark-MXFP4-MQ-IQ2_M_1-Generic.gguf",
      "bytes": 11913885600,
      "decimalGB": 11.9138856,
      "GiB": 11.095670610666275,
      "sha256": "a242cddbdf9baaad660e96d26be99245f2410c154c3a0fa0c6451e3b7109eb01"
    },
    "savings": {
      "bytes": 6978969280,
      "decimalGB": 6.97896928,
      "GiB": 6.499671638011932,
      "percentOfNative": 36.939728401703576
    }
  },
  "tensorAudit": {
    "verificationPassed": true,
    "tensorCount": 866,
    "changedTensorCount": 362,
    "unchangedPayloadsVerifiedByteExact": 504,
    "nativeMxfp4PreservedCount": 144,
    "nativeMxfp4TensorCount": 496,
    "effectiveTypeCounts": {
      "F32": 360,
      "IQ1_M": 48,
      "IQ3_S": 195,
      "IQ3_XXS": 112,
      "IQ4_XS": 3,
      "MXFP4": 144,
      "Q2_K": 1,
      "Q4_K": 2,
      "Q5_K": 1
    }
  },
  "benchmark": {
    "domain": "general",
    "tokenTarget": 32768,
    "chunks": 15,
    "context": 2048,
    "threads": 4,
    "gpuLayers": 0,
    "gpuVisible": false,
    "nativeStandalonePpl": 5.8033,
    "nativeStandalonePplError": 0.11146,
    "paired": {
      "candidatePpl": 6.04002,
      "basePpl": 5.801511,
      "pplDifference": 0.238509,
      "pplRatio": 1.041112,
      "logPplRatio": 0.040289,
      "correlationPercent": 98.61
    },
    "kld": {
      "mean": 0.058879,
      "standardError": 0.001352,
      "maximum": 4.972449,
      "p99_9": 2.321059,
      "p99": 0.597265,
      "p95": 0.195393,
      "p90": 0.119437,
      "median": 0.025196
    },
    "tokenProbability": {
      "meanDeltaPercent": -1.207,
      "rmsDeltaPercent": 7.161,
      "sameTopPercent": 89.951
    },
    "scope": {
      "languageLogits": true,
      "visionProjectorEvaluated": false,
      "mtpTensorsEvaluated": false,
      "note": "llama-perplexity logged block 64 MTP tensors as unused; ordinary KLD primarily measures the changed token embedding and output tensors"
    }
  },
  "imatrixApplicability": {
    "supplied": true,
    "label": "Generic",
    "sha256": "123a92c3ba8cd31ed2887bd348682be5b68c977b12cc30e11c632e7ddf899eaa",
    "entries": 496,
    "changedTensorsWithEntries": 352,
    "changedTensorCount": 362,
    "note": "Coverage is inferred from llama.cpp's per-conversion missing-weight messages; tensors present in the imatrix are supplied to the selected quantizer."
  },
  "artifacts": {
    "corpus": {
      "path": "<REPO_ROOT>/Experiments/MQ-IQ4_XS_1-Generic/benchmark/_ppl_corpora/ppl_corpus_general.txt",
      "bytes": 131514,
      "sha256": "5d38d98dce15f54e9a1a926187b6058e65cd8b3dd9b5cc2729b0a5fd249228b0"
    },
    "referenceLogits": {
      "path": "<REPO_ROOT>/Experiments/MQ-IQ4_XS_1-Generic/benchmark/native-reference/logits/kld_logits_general.bin",
      "bytes": 7621186460,
      "sha256": "604db2df7253cba18a6c0a569ed819ee3065d4ac20cd94ae72f4329e7bba8516"
    },
    "nativeLog": {
      "path": "<REPO_ROOT>/Experiments/MQ-IQ4_XS_1-Generic/benchmark/native-reference/perplexity_general.log",
      "sha256": "bade3445565a354969f7515045507b854bee83f6695eec7490b70eab9c6eebc2"
    },
    "candidateLog": {
      "path": "<REPO_ROOT>/Experiments/MQ-IQ2_M_1-Generic/benchmark/candidate/perplexity_general.log",
      "sha256": "4d9de36b92a99f7c7659847153daac5da553b2bb0fda6c273308af0c5345ba7f"
    },
    "quantizationLog": {
      "path": "<REPO_ROOT>/Experiments/MQ-IQ2_M_1-Generic/quantization.log",
      "sha256": "a81ead0103cdcfaee5b83efec32c20590f4b104a6a0ca103a47bf8ce44d43044"
    }
  }
}