{
  "schemaVersion": 1,
  "createdUtc": "2026-08-26T16:55:11.061354+00:00",
  "experiment": "MQ-IQ2_M_2-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_2-Generic.gguf",
      "bytes": 10691495840,
      "decimalGB": 10.69149584,
      "GiB": 9.957231432199478,
      "sha256": "a7ac992cc59c3ec95105d56c8090fd1208f0ee65bc7571d33c4202afaa8c5dc8"
    },
    "savings": {
      "bytes": 8201359040,
      "decimalGB": 8.20135904,
      "GiB": 7.638110816478729,
      "percentOfNative": 43.40984510859695
    }
  },
  "tensorAudit": {
    "verificationPassed": true,
    "tensorCount": 866,
    "changedTensorCount": 426,
    "unchangedPayloadsVerifiedByteExact": 440,
    "nativeMxfp4PreservedCount": 80,
    "nativeMxfp4TensorCount": 496,
    "effectiveTypeCounts": {
      "F32": 360,
      "IQ1_M": 48,
      "IQ3_S": 82,
      "IQ3_XXS": 288,
      "IQ4_XS": 4,
      "MXFP4": 80,
      "Q2_K": 1,
      "Q3_K": 1,
      "Q5_K": 1,
      "Q6_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": 6.266562,
      "basePpl": 5.801511,
      "pplDifference": 0.465051,
      "pplRatio": 1.08016,
      "logPplRatio": 0.077109,
      "correlationPercent": 97.6
    },
    "kld": {
      "mean": 0.102424,
      "standardError": 0.001765,
      "maximum": 6.221836,
      "p99_9": 2.665715,
      "p99": 0.950551,
      "p95": 0.335705,
      "p90": 0.21974,
      "median": 0.052264
    },
    "tokenProbability": {
      "meanDeltaPercent": -1.851,
      "rmsDeltaPercent": 9.458,
      "sameTopPercent": 85.709
    },
    "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": 416,
    "changedTensorCount": 426,
    "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_2-Generic/benchmark/candidate/perplexity_general.log",
      "sha256": "ada6ba64435a0cc983cecf592f0414766c1b91c23536f4a35c8b6474fc322b67"
    },
    "quantizationLog": {
      "path": "<REPO_ROOT>/Experiments/MQ-IQ2_M_2-Generic/quantization.log",
      "sha256": "46006b16e5e17042a578dddc8e2cb9f19008ca5c308f51183172d8df57372956"
    }
  }
}