{
  "artifact_sha256": {
    "llama-cpp-near-lossless-quality": "e842fdc35d7f00fda95a54e1b51731ba1d196aea45065cc9f46925fdc1d6f862",
    "llama-cpp-quantized-performance-fit": "a88e3f570e2efeaf06b50df9859db2c70d8646aa3a2c94a14e14d5797a2921a5",
    "transformers-safetensors-reference": "e596e9d6205fdc9177569cccd7f8b471b058f66e3630c8e4326d5aad52bd18b6"
  },
  "backend_detail": {
    "llama-cpp-near-lossless-quality": "version: 9991 (e920c523) | built with GNU 15.2.1 for Linux x86_64; binary sha256 fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd; threads 16; parallel slots 4; ctx/slot 512; gpu layers 0",
    "llama-cpp-quantized-performance-fit": "version: 9991 (e920c523) | built with GNU 15.2.1 for Linux x86_64; binary sha256 fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd; threads 16; parallel slots 4; ctx/slot 512; gpu layers 0",
    "transformers-safetensors-reference": "torch 2.10.0+rocm7.13.0a20260513; dtype bfloat16; device cpu; intra-op threads 16"
  },
  "evidence_class": "local-real",
  "host": {
    "accelerator_name": "Radeon 8060S Graphics",
    "accelerator_runtime": "7.13.26183",
    "benchmark_lane": "cpu-controlled-baseline",
    "converter_sha256": "c819f18fb22927b49fabc3b35d1c9e21ee638b3817eccd1bd4efbcc7116eeb4d",
    "cpu_count": 32,
    "cuda_available": true,
    "hostname": "fedora",
    "llama_cpp_commit": "e920c523e3b8a0163fe498af5bf90df35ff51d25",
    "llama_cpp_version": "9991",
    "llama_server_identities": {
      "/run/media/popov/d/DEV/llamacpp/llama.cpp/build/bin/llama-server": {
        "sha256": "fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd",
        "version": "version: 9991 (e920c523) | built with GNU 15.2.1 for Linux x86_64"
      }
    },
    "llama_server_sha256": "fd8fe612970f23e447f2e717cfa51665be06b8d7315ba60556e010f6bca510dd",
    "platform": "Linux-7.0.14-101.fc43.x86_64-x86_64-with-glibc2.42",
    "python": "3.12.13",
    "quantizer_sha256": "bd0cc8c7be6d48aad4755b31062e0e59a887cbadd43dbb8771853d5858bb198f",
    "torch_version": "2.10.0+rocm7.13.0a20260513",
    "transformers_version": "5.13.0"
  },
  "model_id": "Qwen/Qwen2.5-0.5B-Instruct",
  "model_revision": "7ae557604adf67be50417f59c2c2f167def9a775",
  "plan_sha256": "efe24690a9a7164bac6ab3fd0a6b22f078fc08aaefcfb96210ddf154e6050570",
  "provenance": {
    "completed_at": "2026-07-13T16:27:19.647692Z",
    "config_sha256": "00b2cce3e2f281bdf92fc5304ba5cac915a178ffccd3b9a25995ce39c00b90d3",
    "producer": "meshnet_node.recipe_drivers.run_configured_benchmark/v1",
    "run_id": "e4eedadf-22f6-4907-8990-985456961099",
    "schema_version": 1,
    "signature": "owev+/ToswP20C923G6E+srOCUBV5vrjmndVatr9CbTXakiFGqlHrTiEo+aymA4BcSwmG6KJTxlxO6WpLnpcAg==",
    "signature_algorithm": "ed25519",
    "signer_public_key_sha256": "8baca8742d9b3ed0c3fc54929c23f75ec8c1c739900aaf5334780d598ffa84de",
    "started_at": "2026-07-13T16:26:22.361501Z"
  },
  "recipe_runtime": {
    "llama-cpp-near-lossless-quality": {
      "device": "cpu",
      "runtime": "llama.cpp-9991-e920c523",
      "weight_format": "gguf",
      "weight_quantization": "bfloat16"
    },
    "llama-cpp-quantized-performance-fit": {
      "device": "cpu",
      "runtime": "llama.cpp-9991-e920c523",
      "weight_format": "gguf",
      "weight_quantization": "Q4_K_M"
    },
    "transformers-safetensors-reference": {
      "device": "cpu",
      "runtime": "transformers-5.13.0",
      "weight_format": "safetensors",
      "weight_quantization": "bfloat16"
    }
  },
  "recipes": {
    "llama-cpp-near-lossless-quality": {
      "artifact_bytes": 994156448,
      "available": true,
      "concurrency": {
        "1": {
          "aggregate_decode_tokens_per_sec": 86.7339,
          "decode_tokens_per_sec": 98.5178,
          "failures": 0,
          "latency_p50_ms": 333.023,
          "latency_p95_ms": 383.0597,
          "peak_rss_bytes": 1110728704,
          "peak_vram_bytes": 0,
          "prefill_tokens_per_sec": 1717.9451,
          "ttft_p50_ms": 15.069,
          "ttft_p95_ms": 63.766
        },
        "4": {
          "aggregate_decode_tokens_per_sec": 222.788,
          "decode_tokens_per_sec": 76.6297,
          "failures": 0,
          "latency_p50_ms": 490.8738,
          "latency_p95_ms": 646.26,
          "peak_rss_bytes": 1139466240,
          "peak_vram_bytes": 0,
          "prefill_tokens_per_sec": 859.8985,
          "ttft_p50_ms": 32.445,
          "ttft_p95_ms": 218.387
        }
      },
      "device": "cpu",
      "lane": "quality"
    },
    "llama-cpp-quantized-performance-fit": {
      "artifact_bytes": 397807520,
      "available": true,
      "concurrency": {
        "1": {
          "aggregate_decode_tokens_per_sec": 139.2693,
          "decode_tokens_per_sec": 207.712,
          "failures": 0,
          "latency_p50_ms": 168.3307,
          "latency_p95_ms": 305.1338,
          "peak_rss_bytes": 542081024,
          "peak_vram_bytes": 0,
          "prefill_tokens_per_sec": 967.0195,
          "ttft_p50_ms": 21.582,
          "ttft_p95_ms": 147.859
        },
        "4": {
          "aggregate_decode_tokens_per_sec": 195.6789,
          "decode_tokens_per_sec": 76.9497,
          "failures": 0,
          "latency_p50_ms": 437.9196,
          "latency_p95_ms": 885.5355,
          "peak_rss_bytes": 573259776,
          "peak_vram_bytes": 0,
          "prefill_tokens_per_sec": 572.4424,
          "ttft_p50_ms": 48.127,
          "ttft_p95_ms": 416.531
        }
      },
      "device": "cpu",
      "lane": "performance-fit"
    },
    "transformers-safetensors-reference": {
      "artifact_bytes": 999586347,
      "available": true,
      "concurrency": {
        "1": {
          "aggregate_decode_tokens_per_sec": 35.4722,
          "decode_tokens_per_sec": 40.7545,
          "failures": 0,
          "latency_p50_ms": 818.3864,
          "latency_p95_ms": 1258.0673,
          "peak_rss_bytes": 1941458944,
          "peak_vram_bytes": 0,
          "prefill_tokens_per_sec": 625.6467,
          "ttft_p50_ms": 40.0018,
          "ttft_p95_ms": 195.2551
        },
        "4": {
          "aggregate_decode_tokens_per_sec": 46.5375,
          "decode_tokens_per_sec": 12.9506,
          "failures": 0,
          "latency_p50_ms": 2481.8662,
          "latency_p95_ms": 3365.8395,
          "peak_rss_bytes": 2104832000,
          "peak_vram_bytes": 0,
          "prefill_tokens_per_sec": 264.0101,
          "ttft_p50_ms": 97.0403,
          "ttft_p95_ms": 429.0665
        }
      },
      "device": "cpu",
      "lane": "quality"
    }
  },
  "reference_recipe_id": "transformers-safetensors-reference"
}