{
  "configuration": {
    "machine": {
      "platform": "apple-silicon",
      "chip": "M4 Pro",
      "model": "Mac16,7",
      "cpuCores": 14,
      "gpuCores": 20,
      "memoryGiB": 24,
      "osFamily": "macOS",
      "osVersion": "26.3",
      "osBuild": "25D125"
    },
    "runtime": {
      "name": "llama.cpp",
      "version": "b11429",
      "commit": "d81235049",
      "binarySha256": "51afbf4ea6485b9ada19e99af97181f12baca42ef704b1e291c26a9ac0644eae"
    },
    "python": "3.12.14",
    "pypdf": "6.10.0",
    "model": {
      "id": "Qwen3-4B",
      "quantization": "Q4_K_M",
      "repository": "Qwen/Qwen3-4B-GGUF",
      "revision": "bc640142c66e1fdd12af0bd68f40445458f3869b",
      "file": "Qwen3-4B-Q4_K_M.gguf",
      "bytes": 2497280256,
      "sha256": "7485fe6f11af29433bc51cab58009521f205840f5b4ae3a32fa7f92e8534fdf5",
      "license": "Apache-2.0"
    }
  },
  "workflowVersion": "1.5.0",
  "runnerSha256": "d5e3c68878af3926c8844e7406a5f9f2666c133eabe624bc34836a85161f17b2",
  "generationSeed": 271828,
  "context": 8192,
  "temperature": 0,
  "maxOutputTokens": 512,
  "thinking": false,
  "cpuThreads": 10,
  "gpuOffload": "full Metal",
  "parallel": 1,
  "flashAttention": true,
  "kv": "F16",
  "retrieval": "Local BM25 pages and generic field/clause selection; source-ID selection then local sufficiency inference",
  "answerModelRequests": [
    79,
    79,
    79
  ],
  "warmupRequests": 3,
  "cachePolicy": "cache_prompt false; no claim that OS file caches were flushed.",
  "timingBoundary": "runner.ask entry through its complete returned answer, source resolution and sufficiency check; excludes prior PDF import/index, cold start, warmup and later grading.",
  "nativeEgressComparison": "unverified; no comparative privacy claim"
}