{
  "target": "FP8",
  "model": "/mnt/c/Users/chunk/OneDrive/Documents/quant3.8/qwen38-cuda-quants/outputs/Qwen3.8-27B-FP8",
  "created_utc": "2026-08-18T08:12:26+00:00",
  "smoke_test": false,
  "execution_mode": "RTX 4070 + CPU offload/auto map",
  "hardware": "NVIDIA GeForce RTX 4070 12 GB (not 4070 Ti)",
  "device_map_summary": {
    "cpu": 59,
    "cuda:0": 9
  },
  "repetitions": 1,
  "prompt_tokens": 8,
  "requested_decode_tokens": 1,
  "warmup_tokens": 1,
  "cold_load_seconds": 135.15700745499998,
  "warm_load_seconds": null,
  "single_load_memory_safe_mode": true,
  "ttft_seconds_median": 246.20996074599998,
  "prefill_tok_s_median": 0.049479823627132595,
  "decode_tok_s_median": 0.023630125161260673,
  "end_to_end_generated_tok_s_median": 0.004901938544242578,
  "median_generated_tokens": 1.0,
  "peak_vram_gib": 11.6689453125,
  "peak_vram_source": "nvidia-smi device-wide memory.used sampled every 0.5 seconds",
  "baseline_device_memory_gib": 1.2080078125,
  "device_memory_total_gib": 11.994140625,
  "torch_allocator_peak_gib": 10.919785499572754,
  "device_memory_sampler_error": null,
  "process_rss_gib": 47.185646057128906,
  "system_used_gib_at_end": 48.21872329711914,
  "raw": {
    "prefill_seconds": [
      161.68206378999997
    ],
    "ttft_seconds": [
      246.20996074599998
    ],
    "generation_seconds": [
      204.00092554700007
    ],
    "generated_tokens": [
      1
    ]
  },
  "passed": true
}