{
  "timestamp": "20260629_102625",
  "prompt": "Explain how gradient descent works in three concise sentences.",
  "max_tokens": 300,
  "runs": 6,
  "results": {
    "Ollama\n(Q4_K_M)": [
      {
        "ttft": 1.634000250021927,
        "total": 11.055586000031326,
        "tokens": 256,
        "tps": 27.171648089469258
      },
      {
        "ttft": 0.5513010839931667,
        "total": 10.531367084011436,
        "tokens": 256,
        "tps": 25.651135217461704
      },
      {
        "ttft": 0.4852821250096895,
        "total": 11.444887874997221,
        "tokens": 256,
        "tps": 23.35850509937467
      },
      {
        "ttft": 0.67359745799331,
        "total": 12.057259958004579,
        "tokens": 256,
        "tps": 22.488368994729825
      },
      {
        "ttft": 0.6853210419649258,
        "total": 12.4251498329686,
        "tokens": 256,
        "tps": 21.806110402784924
      },
      {
        "ttft": 1.0419203329947777,
        "total": 11.229581249994226,
        "tokens": 256,
        "tps": 25.12843774699821
      }
    ],
    "vLLM\n(AWQ-INT4)": [
      {
        "ttft": 0.3202166249975562,
        "total": 7.929881749965716,
        "tokens": 300,
        "tps": 39.4235495162105
      },
      {
        "ttft": 0.27499408402945846,
        "total": 7.884857708995696,
        "tokens": 300,
        "tps": 39.422520522243424
      },
      {
        "ttft": 0.3822782500064932,
        "total": 7.98455999995349,
        "tokens": 300,
        "tps": 39.461837434634035
      },
      {
        "ttft": 0.333280291990377,
        "total": 7.941394416964613,
        "tokens": 300,
        "tps": 39.43158623449782
      },
      {
        "ttft": 0.2996448330231942,
        "total": 7.909792166028637,
        "tokens": 300,
        "tps": 39.42105213663217
      },
      {
        "ttft": 0.296181040990632,
        "total": 7.916995125007816,
        "tokens": 300,
        "tps": 39.36587329739024
      }
    ]
  }
}