Files
Christian Meyer 407af8099b
Some checks failed
CI / test (push) Has been cancelled
CI / test (pull_request) Has been cancelled
docs: record Qwen MLX benchmark results
2026-08-31 16:39:37 +02:00

54 lines
1.7 KiB
JSON

[
{
"runtime": "vllm-metal",
"model": "qwen3.8-27b-nvfp4",
"concurrency": 1,
"requests": 5,
"successes": 5,
"failures": 0,
"ttft_s_mean": 0.3338013501954265,
"ttft_s_p50": 0.37227433401858434,
"ttft_s_p95": 0.4201282836031169,
"total_s_mean": 5.444907250197138,
"total_s_p50": 5.454897999996319,
"total_s_p95": 5.562144016823732,
"prompt_tps_mean": null,
"prompt_tps_p50": null,
"prompt_tps_p95": null,
"decode_tps_mean": 25.04504255080693,
"decode_tps_p50": 24.962500989743333,
"decode_tps_p95": 25.32382313060655,
"request_tps_mean": 23.517575676354507,
"request_tps_p50": 23.465150035818517,
"request_tps_p95": 24.196276605031606,
"aggregate_output_tps_mean": 23.516827822391825,
"aggregate_output_tps_p50": 23.464397444683396,
"aggregate_output_tps_p95": 24.195480643338048
},
{
"runtime": "vllm-metal",
"model": "qwen3.8-27b-nvfp4",
"concurrency": 4,
"requests": 20,
"successes": 20,
"failures": 0,
"ttft_s_mean": 1.1358489938022103,
"ttft_s_p50": 1.1691114795103204,
"ttft_s_p95": 1.2360623297834537,
"total_s_mean": 9.343862856202758,
"total_s_p50": 9.272835896001197,
"total_s_p95": 9.591099269420374,
"prompt_tps_mean": null,
"prompt_tps_p50": null,
"prompt_tps_p95": null,
"decode_tps_mean": 15.572524640705884,
"decode_tps_p50": 15.580143217705817,
"decode_tps_p95": 15.920671319893613,
"request_tps_mean": 13.679827878866371,
"request_tps_p50": 13.803600866803595,
"request_tps_p95": 13.831739950302437,
"aggregate_output_tps_mean": 54.66256367620249,
"aggregate_output_tps_p50": 54.89183177619698,
"aggregate_output_tps_p95": 55.24148726503248
}
]