{
  "run_id": "20260831T133721Z",
  "created_at": "2026-08-31T13:38:28.661722+00:00",
  "host": {
    "platform": "macOS-15.6-arm64-arm-64bit",
    "machine": "arm64",
    "python": "3.12.8"
  },
  "arguments": {
    "model": "mlx-community/Qwen3.8-27B-mxfp8",
    "label": "qwen3.8-27b-mxfp8",
    "warmups": 2,
    "rounds": 5,
    "max_tokens": 128,
    "seed": 42,
    "output_dir": "/Users/christianmeyer/Documents/git/lai_automatisierung/benchmarks/inference/direct-results"
  },
  "load_s": 5.387068083975464,
  "mlx_version": "0.32.0",
  "device": "Device(gpu, 0)",
  "prompts": {
    "short": "In exactly four concise bullet points, explain why database transactions are useful. Do not use a heading.",
    "medium": "You are reviewing a Laravel service that transfers money between two accounts. Explain the failure modes involving concurrency, partial writes, retries, and audit logs. Then provide a robust implementation plan. Keep the response technical and concise.",
    "code": "Write a Python 3.12 function named merge_intervals that accepts a list of integer pairs, validates each pair, merges overlapping or adjacent intervals, and returns sorted tuples. Include type hints, a short docstring, and five assert-based examples. Output only code."
  },
  "summary": {
    "runtime": "mlx-lm-direct",
    "model": "qwen3.8-27b-mxfp8",
    "requests": 5,
    "successes": 5,
    "ttft_s_mean": 0.6405866249930113,
    "ttft_s_p50": 0.6006166669540107,
    "ttft_s_p95": 0.993492508213967,
    "total_s_mean": 8.97830267478712,
    "total_s_p50": 8.952084249991458,
    "total_s_p95": 9.543902474397328,
    "prompt_tps_mean": 77.25518114106583,
    "prompt_tps_p50": 69.803885982221,
    "prompt_tps_p95": 108.54351756783554,
    "decode_tps_mean": 15.141694584402668,
    "decode_tps_p50": 15.417877788139895,
    "decode_tps_p95": 15.90376325022775,
    "request_tps_mean": 14.036390549836813,
    "request_tps_p50": 14.298346220336581,
    "request_tps_p95": 14.998850485179887,
    "peak_memory_gb": 28.05746427
  }
}