{
  "schemaVersion": 1,
  "createdUtc": "2026-08-26T05:12:53.532885+00:00",
  "experiment": "UD-Q4_K_S-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-UD-Q4_K_S-Unsloth.gguf",
      "bytes": 14547122080,
      "decimalGB": 14.54712208,
      "GiB": 13.548063188791275,
      "sha256": "b077ade0bd8aab9a1e5386ed09d72b6a24bca62fd71ec16c049b29a740f81ff3"
    },
    "savings": {
      "bytes": 4345732800,
      "decimalGB": 4.3457328,
      "GiB": 4.047279059886932,
      "percentOfNative": 23.001991110408614
    }
  },
  "tensorAudit": {
    "verificationPassed": true,
    "tensorCount": 866,
    "changedTensorCount": 44,
    "unchangedPayloadsVerifiedByteExact": 822,
    "nativeMxfp4PreservedCount": 462,
    "nativeMxfp4TensorCount": 496,
    "effectiveTypeCounts": {
      "F32": 360,
      "IQ2_S": 1,
      "IQ2_XS": 1,
      "IQ3_S": 15,
      "IQ3_XXS": 5,
      "MXFP4": 462,
      "Q3_K": 13,
      "Q6_K": 7,
      "Q8_0": 2
    }
  },
  "benchmark": {
    "domain": "general",
    "tokenTarget": 32768,
    "chunks": 15,
    "context": 2048,
    "threads": 4,
    "gpuLayers": 0,
    "gpuVisible": false,
    "nativeStandalonePpl": 5.8033,
    "nativeStandalonePplError": 0.11146,
    "paired": {
      "candidatePpl": 5.80558,
      "basePpl": 5.801511,
      "pplDifference": 0.004069,
      "pplRatio": 1.000701,
      "logPplRatio": 0.000701,
      "correlationPercent": 99.91
    },
    "kld": {
      "mean": 0.00345,
      "standardError": 9.9e-05,
      "maximum": 0.602664,
      "p99_9": 0.191006,
      "p99": 0.034935,
      "p95": 0.011178,
      "p90": 0.006836,
      "median": 0.001342
    },
    "tokenProbability": {
      "meanDeltaPercent": -0.036,
      "rmsDeltaPercent": 1.809,
      "sameTopPercent": 97.471
    },
    "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": 34,
    "changedTensorCount": 44,
    "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/UD-Q4_K_S-Unsloth/benchmark/candidate/perplexity_general.log",
      "sha256": "b3143cf37e33d10ea59943d4416698b43e862c919507efac6680072df9bddc96"
    },
    "quantizationLog": {
      "path": "<REPO_ROOT>/Experiments/UD-Q4_K_S-Unsloth/quantization.log",
      "sha256": "88a570e747b518bde9a958f7eed395d7f2629b7d559a92f9a7ff94d19bdcc000"
    }
  }
}