{
  "recorded_on": "2026-10-20",
  "environment": {
    "python": "3.15.0",
    "platform": "macOS-27.0.1-arm64-arm-64bit-Mach-O",
    "hardware": "Apple M4 Pro (Mac16,7), 48 GiB unified memory, macOS 27.0.1",
    "memory_bytes": 51539607552,
    "ollama": "0.32.14"
  },
  "results": [
    {
      "profile": {
        "tag": "qwen3.5:0.8b",
        "digest": "de63045f29755d4721c09d54c9b45c2dadb644f4fd7d604d4cac90d96049971c",
        "download_bytes": 1322069277,
        "format": "gguf",
        "parameter_size": "752.39M",
        "quantization": "Q8_0",
        "capabilities": [
          "completion",
          "vision",
          "tools",
          "thinking"
        ],
        "context_length": 262144,
        "artifact_license": "apache-2.0",
        "problems": []
      },
      "load_request_ms": 1744.6,
      "development": [
        {
          "id": "dev-bug-1",
          "expected": "bug",
          "answer": "bug",
          "status": "pass",
          "reason": "expected label",
          "client_ms": 220.5,
          "done_reason": "stop",
          "server_load_ms": 149.7,
          "input_tokens": 49,
          "output_tokens": 2
        },
        {
          "id": "dev-bug-2",
          "expected": "bug",
          "answer": "bug",
          "status": "pass",
          "reason": "expected label",
          "client_ms": 220.8,
          "done_reason": "stop",
          "server_load_ms": 165.6,
          "input_tokens": 49,
          "output_tokens": 2
        },
        {
          "id": "dev-bug-3",
          "expected": "bug",
          "answer": "bug",
          "status": "pass",
          "reason": "expected label",
          "client_ms": 211.6,
          "done_reason": "stop",
          "server_load_ms": 151.4,
          "input_tokens": 56,
          "output_tokens": 2
        },
        {
          "id": "dev-question-1",
          "expected": "question",
          "answer": "bug",
          "status": "fail",
          "reason": "wrong label",
          "client_ms": 207.9,
          "done_reason": "stop",
          "server_load_ms": 149.9,
          "input_tokens": 44,
          "output_tokens": 2
        },
        {
          "id": "dev-question-2",
          "expected": "question",
          "answer": "bug",
          "status": "fail",
          "reason": "wrong label",
          "client_ms": 213.5,
          "done_reason": "stop",
          "server_load_ms": 157.1,
          "input_tokens": 47,
          "output_tokens": 2
        },
        {
          "id": "dev-question-3",
          "expected": "question",
          "answer": "bug",
          "status": "fail",
          "reason": "wrong label",
          "client_ms": 214.7,
          "done_reason": "stop",
          "server_load_ms": 151.0,
          "input_tokens": 44,
          "output_tokens": 2
        },
        {
          "id": "dev-feature-1",
          "expected": "feature",
          "answer": "bug",
          "status": "fail",
          "reason": "wrong label",
          "client_ms": 216.7,
          "done_reason": "stop",
          "server_load_ms": 149.9,
          "input_tokens": 47,
          "output_tokens": 2
        },
        {
          "id": "dev-feature-2",
          "expected": "feature",
          "answer": "feature",
          "status": "pass",
          "reason": "expected label",
          "client_ms": 208.8,
          "done_reason": "stop",
          "server_load_ms": 151.5,
          "input_tokens": 46,
          "output_tokens": 2
        },
        {
          "id": "dev-feature-3",
          "expected": "feature",
          "answer": "yes",
          "status": "fail",
          "reason": "not an allowed label",
          "client_ms": 215.4,
          "done_reason": "stop",
          "server_load_ms": 156.4,
          "input_tokens": 47,
          "output_tokens": 2
        }
      ],
      "held_out": [
        {
          "id": "held-bug-1",
          "expected": "bug",
          "answer": "bug",
          "status": "pass",
          "reason": "expected label",
          "client_ms": 202.8,
          "done_reason": "stop",
          "server_load_ms": 146.6,
          "input_tokens": 47,
          "output_tokens": 2
        },
        {
          "id": "held-bug-2",
          "expected": "bug",
          "answer": "bug",
          "status": "pass",
          "reason": "expected label",
          "client_ms": 212.3,
          "done_reason": "stop",
          "server_load_ms": 151.5,
          "input_tokens": 47,
          "output_tokens": 2
        },
        {
          "id": "held-question-1",
          "expected": "question",
          "answer": "bug",
          "status": "fail",
          "reason": "wrong label",
          "client_ms": 201.3,
          "done_reason": "stop",
          "server_load_ms": 146.1,
          "input_tokens": 45,
          "output_tokens": 2
        },
        {
          "id": "held-question-2",
          "expected": "question",
          "answer": "bug",
          "status": "fail",
          "reason": "wrong label",
          "client_ms": 204.5,
          "done_reason": "stop",
          "server_load_ms": 146.5,
          "input_tokens": 47,
          "output_tokens": 2
        },
        {
          "id": "held-feature-1",
          "expected": "feature",
          "answer": "feature",
          "status": "pass",
          "reason": "expected label",
          "client_ms": 204.6,
          "done_reason": "stop",
          "server_load_ms": 145.6,
          "input_tokens": 45,
          "output_tokens": 2
        },
        {
          "id": "held-feature-2",
          "expected": "feature",
          "answer": "feature",
          "status": "pass",
          "reason": "expected label",
          "client_ms": 204.8,
          "done_reason": "stop",
          "server_load_ms": 148.3,
          "input_tokens": 47,
          "output_tokens": 2
        }
      ]
    },
    {
      "profile": {
        "tag": "gemma4:e2b",
        "digest": "b37049369adfe3d2b653af0ab301a062ca5cbe96ace6aa0d3f2559ee9b563fc2",
        "download_bytes": 4587156505,
        "format": "gguf",
        "parameter_size": "4.6B",
        "quantization": "Q4_K_M",
        "capabilities": [
          "completion",
          "vision",
          "audio",
          "tools",
          "thinking"
        ],
        "context_length": 131072,
        "artifact_license": "apache-2.0",
        "problems": []
      },
      "load_request_ms": 3411.8,
      "development": [
        {
          "id": "dev-bug-1",
          "expected": "bug",
          "answer": "bug",
          "status": "pass",
          "reason": "expected label",
          "client_ms": 383.2,
          "done_reason": "stop",
          "server_load_ms": 234.1,
          "input_tokens": 46,
          "output_tokens": 2
        },
        {
          "id": "dev-bug-2",
          "expected": "bug",
          "answer": "bug",
          "status": "pass",
          "reason": "expected label",
          "client_ms": 364.2,
          "done_reason": "stop",
          "server_load_ms": 235.1,
          "input_tokens": 46,
          "output_tokens": 2
        },
        {
          "id": "dev-bug-3",
          "expected": "bug",
          "answer": "bug",
          "status": "pass",
          "reason": "expected label",
          "client_ms": 354.8,
          "done_reason": "stop",
          "server_load_ms": 232.4,
          "input_tokens": 53,
          "output_tokens": 2
        },
        {
          "id": "dev-question-1",
          "expected": "question",
          "answer": "question",
          "status": "pass",
          "reason": "expected label",
          "client_ms": 359.2,
          "done_reason": "stop",
          "server_load_ms": 235.3,
          "input_tokens": 41,
          "output_tokens": 2
        },
        {
          "id": "dev-question-2",
          "expected": "question",
          "answer": "question",
          "status": "pass",
          "reason": "expected label",
          "client_ms": 356.1,
          "done_reason": "stop",
          "server_load_ms": 232.1,
          "input_tokens": 44,
          "output_tokens": 2
        },
        {
          "id": "dev-question-3",
          "expected": "question",
          "answer": "question",
          "status": "pass",
          "reason": "expected label",
          "client_ms": 363.6,
          "done_reason": "stop",
          "server_load_ms": 238.7,
          "input_tokens": 41,
          "output_tokens": 2
        },
        {
          "id": "dev-feature-1",
          "expected": "feature",
          "answer": "feature",
          "status": "pass",
          "reason": "expected label",
          "client_ms": 367.1,
          "done_reason": "stop",
          "server_load_ms": 239.4,
          "input_tokens": 44,
          "output_tokens": 2
        },
        {
          "id": "dev-feature-2",
          "expected": "feature",
          "answer": "feature",
          "status": "pass",
          "reason": "expected label",
          "client_ms": 366.0,
          "done_reason": "stop",
          "server_load_ms": 237.0,
          "input_tokens": 43,
          "output_tokens": 2
        },
        {
          "id": "dev-feature-3",
          "expected": "feature",
          "answer": "feature",
          "status": "pass",
          "reason": "expected label",
          "client_ms": 361.2,
          "done_reason": "stop",
          "server_load_ms": 237.2,
          "input_tokens": 44,
          "output_tokens": 2
        }
      ],
      "held_out": [
        {
          "id": "held-bug-1",
          "expected": "bug",
          "answer": "bug",
          "status": "pass",
          "reason": "expected label",
          "client_ms": 357.6,
          "done_reason": "stop",
          "server_load_ms": 233.2,
          "input_tokens": 44,
          "output_tokens": 2
        },
        {
          "id": "held-bug-2",
          "expected": "bug",
          "answer": "bug",
          "status": "pass",
          "reason": "expected label",
          "client_ms": 356.8,
          "done_reason": "stop",
          "server_load_ms": 233.4,
          "input_tokens": 44,
          "output_tokens": 2
        },
        {
          "id": "held-question-1",
          "expected": "question",
          "answer": "question",
          "status": "pass",
          "reason": "expected label",
          "client_ms": 355.8,
          "done_reason": "stop",
          "server_load_ms": 232.3,
          "input_tokens": 42,
          "output_tokens": 2
        },
        {
          "id": "held-question-2",
          "expected": "question",
          "answer": "question",
          "status": "pass",
          "reason": "expected label",
          "client_ms": 357.0,
          "done_reason": "stop",
          "server_load_ms": 231.5,
          "input_tokens": 44,
          "output_tokens": 2
        },
        {
          "id": "held-feature-1",
          "expected": "feature",
          "answer": "feature",
          "status": "pass",
          "reason": "expected label",
          "client_ms": 363.1,
          "done_reason": "stop",
          "server_load_ms": 238.3,
          "input_tokens": 42,
          "output_tokens": 2
        },
        {
          "id": "held-feature-2",
          "expected": "feature",
          "answer": "feature",
          "status": "pass",
          "reason": "expected label",
          "client_ms": 360.3,
          "done_reason": "stop",
          "server_load_ms": 228.6,
          "input_tokens": 45,
          "output_tokens": 2
        }
      ]
    }
  ]
}
