{
  "schemaVersion": "1.0.0",
  "runId": "qwen38-27b-q4km-rtx4090-f16kv-125952-1787105636",
  "model": {
    "id": "qwen3.8-27b",
    "repository": "Qwen/Qwen3.8-27B",
    "revision": "1d4bf0f2ff6012fd82039f2fa52739d0dd7c60c0"
  },
  "artifact": {
    "filename": "Qwen3.8-27B-Q4_K_M.gguf",
    "repository": "unsloth/Qwen3.8-27B-GGUF",
    "revision": "f1bfb127c64f7072bdd2cad55f258b9c8b2910fe",
    "sha256": "7e78da5d7e3ae28d178121f58646953305f3e5bd3cb46f4a75584e8b6c6fe169",
    "sizeBytes": 17106775008,
    "quantization": "q4-k-m",
    "contentHashSource": "Hugging Face x-linked-etag and independent local SHA-256"
  },
  "runtime": {
    "name": "llama.cpp",
    "version": "version: 0.1.2-dev (build 1, commit 6d0549831)",
    "commit": "6d05498314db1b57f81c271080018aa2d0b89be9",
    "command": [
      "/kingy-local-lab/llama.cpp/build/bin/llama-server",
      "-m",
      "/kingy-local-lab/models/Qwen3.8-27B-Q4_K_M.gguf",
      "-c",
      "125952",
      "-ngl",
      "999",
      "-ctk",
      "f16",
      "-ctv",
      "f16",
      "-b",
      "512",
      "-ub",
      "512",
      "--parallel",
      "1",
      "--host",
      "127.0.0.1",
      "--port",
      "8080",
      "--metrics",
      "--no-mmap"
    ]
  },
  "environment": {
    "os": "Linux-6.14.0-29-generic-x86_64-with-glibc2.39",
    "hardware": "NVIDIA GeForce RTX 4090",
    "hardwareId": "rtx-4090-24gb",
    "gpuUuid": "GPU-26f05cd8-3563-5afe-e659-1dcadfa30718",
    "driverVersion": "580.65.06",
    "memoryBytes": 134217728000,
    "environmentLog": "logs/environment.txt",
    "cloudProvider": "RunPod Secure Cloud",
    "cloudRegion": "EUR-IS-1",
    "podId": "dto9mj08pd9xy0",
    "allocatedVcpu": 64,
    "cpu": "AMD EPYC 7702 64-Core Processor",
    "hostVisibleCpuCount": 256,
    "hostVisibleMemoryBytes": 540790554624,
    "allocationSource": "RunPod console: 64 vCPU and 125 GB; host-visible values retained separately",
    "gpuMemoryMiB": 24564,
    "cudaDriverCapability": "13.0",
    "cudaToolkit": "12.8.93"
  },
  "configuration": {
    "contextTokens": 125952,
    "kvCacheType": "f16",
    "batchSize": 512,
    "microBatchSize": 512,
    "parallelism": 1,
    "gpuLayersRequested": 999,
    "offload": "all model layers and KV cache on GPU; no CPU layer offload",
    "phase": "boundary"
  },
  "measurements": {
    "warmupRuns": 1,
    "measuredRuns": 0,
    "peakMemoryBytes": 25230835712,
    "peakMemoryMiB": 24062,
    "loadSeconds": 6.131869122385979,
    "promptTokensPerSecond": 0,
    "generationTokensPerSecond": 0,
    "timeToFirstTokenSeconds": 0,
    "outcome": "oom",
    "actualPromptTokens": [],
    "actualGenerationTokens": [],
    "rawRepeats": [],
    "failureDetail": "URLError(ConnectionRefusedError(111, 'Connection refused'))",
    "statistics": {
      "promptTokensPerSecond": null,
      "generationTokensPerSecond": null,
      "timeToFirstTokenSeconds": null
    }
  },
  "evaluation": null,
  "timestamp": "2026-08-19T02:13:48.854566Z",
  "evidenceState": "observed",
  "reviewer": "Kingy AI Local Lab evidence review",
  "rawEvidence": {
    "requestLog": "logs/raw-boundary-125952.json",
    "serverLog": "logs/server-boundary-125952.log",
    "memoryLog": "logs/memory-boundary-125952.csv",
    "archiveUrl": "/data/evidence/kingy-qwen38-4090-evidence.tgz",
    "archiveSha256": "028781080144a73a611a6b729edf1af8e8fd4173bd047ec3a3dfc4bab86359b9"
  },
  "review": {
    "status": "passed",
    "reviewedAt": "2026-08-19T02:20:00Z",
    "checks": [
      "artifact size and SHA-256 match the pinned Hugging Face revision response",
      "single NVIDIA GeForce RTX 4090 with 24,564 MiB reported by nvidia-smi",
      "llama.cpp commit, driver, CUDA, OS, CPU and memory evidence retained",
      "FP16 K/V cache, one slot and -ngl 999; no CPU layer offload fallback",
      "one warm-up and three measured repetitions for every successful context",
      "512 prompt tokens and 128 generated tokens in every measured success",
      "CUDA OOM failures and the 1,024-token boundary bracket retained"
    ],
    "limitations": [
      "RunPod host allocation is not a retail desktop platform and may differ in CPU, thermals and power behavior",
      "llama.cpp ignored the artifact's extra blk.64/MTP tensors; quality was not evaluated",
      "the measured boundary is an allocated-context VRAM-fit boundary; successful requests used 512 prompt tokens and 128 generated tokens, not a near-full-context prompt",
      "the boundary is established for this exact artifact, runtime commit, FP16 KV cache and batch settings only",
      "the upstream base revision is a pinned model record; the GGUF conversion lineage to that exact base commit was not independently established"
    ]
  },
  "receiptHash": "sha256:d3f7e6f9d3fee41ec208865c344aec732f88720574a84c00ea0ee7179b07c375"
}