{
  "schemaVersion": 1,
  "createdUtc": "2026-08-26T20:08:16.150125+00:00",
  "experiment": "MQ-IQ2_XXS_1-Unsloth",
  "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_XXS_1-Unsloth.gguf",
      "bytes": 8223819680,
      "decimalGB": 8.22381968,
      "GiB": 7.659028917551041,
      "sha256": "84ab6e9cea4e1f7091e00a0b115ffa245e95f8b59e87e6e8ffdfdf3ee71dc441"
    },
    "savings": {
      "bytes": 10669035200,
      "decimalGB": 10.6690352,
      "GiB": 9.936313331127167,
      "percentOfNative": 56.47127058226787
    }
  },
  "tensorAudit": {
    "verificationPassed": true,
    "tensorCount": 866,
    "changedTensorCount": 390,
    "unchangedPayloadsVerifiedByteExact": 476,
    "nativeMxfp4PreservedCount": 108,
    "nativeMxfp4TensorCount": 496,
    "effectiveTypeCounts": {
      "BF16": 8,
      "F32": 360,
      "IQ1_M": 19,
      "IQ1_S": 91,
      "IQ2_S": 40,
      "IQ2_XS": 46,
      "IQ2_XXS": 131,
      "IQ3_S": 10,
      "IQ3_XXS": 45,
      "MXFP4": 108,
      "Q2_K": 6,
      "Q3_K": 2
    }
  },
  "benchmark": {
    "domain": "general",
    "tokenTarget": 32768,
    "chunks": 15,
    "context": 2048,
    "threads": 4,
    "gpuLayers": 0,
    "gpuVisible": false,
    "nativeStandalonePpl": 5.8033,
    "nativeStandalonePplError": 0.11146,
    "paired": {
      "candidatePpl": 7.704137,
      "basePpl": 5.801511,
      "pplDifference": 1.902626,
      "pplRatio": 1.327953,
      "logPplRatio": 0.283639,
      "correlationPercent": 92.52
    },
    "kld": {
      "mean": 0.321797,
      "standardError": 0.004179,
      "maximum": 9.210259,
      "p99_9": 5.867157,
      "p99": 2.483742,
      "p95": 1.134889,
      "p90": 0.741691,
      "median": 0.177414
    },
    "tokenProbability": {
      "meanDeltaPercent": -6.684,
      "rmsDeltaPercent": 17.362,
      "sameTopPercent": 76.729
    },
    "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": "Unsloth",
    "sha256": "0ee5b10bd0c2fa2127c6f4b43dbfe1efd71e383b63217af9dade1de36599f1c1",
    "entries": 496,
    "changedTensorsWithEntries": 388,
    "changedTensorCount": 390,
    "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_XXS_1-Unsloth/benchmark/candidate/perplexity_general.log",
      "sha256": "6c608d8e0d95221b088067d42a08fe10bb45e1e63dde385a460f3821e1081f72"
    },
    "quantizationLog": {
      "path": "<REPO_ROOT>/Experiments/MQ-IQ2_XXS_1-Unsloth/quantization.log",
      "sha256": "c05ffce3f2845c3daebdad7f68d5cd2672188f6d628263e0657064e5ab3ec22d"
    }
  }
}