54 lines
1.8 KiB
JSON
54 lines
1.8 KiB
JSON
[
|
|
{
|
|
"runtime": "ollama",
|
|
"model": "qwen3.8:27b-mlx",
|
|
"concurrency": 1,
|
|
"requests": 5,
|
|
"successes": 5,
|
|
"failures": 0,
|
|
"ttft_s_mean": 0.18287834140937775,
|
|
"ttft_s_p50": 0.11936691601295024,
|
|
"ttft_s_p95": 0.3934195415815338,
|
|
"total_s_mean": 2.769790649821516,
|
|
"total_s_p50": 2.7544727920321748,
|
|
"total_s_p95": 3.450829833233729,
|
|
"prompt_tps_mean": 1201063.1140147406,
|
|
"prompt_tps_p50": 816.5668113066018,
|
|
"prompt_tps_p95": 3147950.5530253737,
|
|
"decode_tps_mean": 44.301349906835995,
|
|
"decode_tps_p50": 45.72630609321048,
|
|
"decode_tps_p95": 52.87492274071074,
|
|
"request_tps_mean": 42.02276635113332,
|
|
"request_tps_p50": 44.19526212378514,
|
|
"request_tps_p95": 46.37707708697445,
|
|
"aggregate_output_tps_mean": 42.01338924160581,
|
|
"aggregate_output_tps_p50": 44.18819214792146,
|
|
"aggregate_output_tps_p95": 46.368391249450006
|
|
},
|
|
{
|
|
"runtime": "ollama",
|
|
"model": "qwen3.8:27b-mlx",
|
|
"concurrency": 4,
|
|
"requests": 20,
|
|
"successes": 20,
|
|
"failures": 0,
|
|
"ttft_s_mean": 5.296346539442311,
|
|
"ttft_s_p50": 5.078280103509314,
|
|
"ttft_s_p95": 10.691154320855276,
|
|
"total_s_mean": 8.731022270751419,
|
|
"total_s_p50": 8.619212541496381,
|
|
"total_s_p95": 14.520918775268365,
|
|
"prompt_tps_mean": 4873110.971654413,
|
|
"prompt_tps_p50": 3843030.8359358422,
|
|
"prompt_tps_p95": 9861582.229537027,
|
|
"decode_tps_mean": 33.61516109813652,
|
|
"decode_tps_p50": 34.997484039567254,
|
|
"decode_tps_p95": 40.1951363429803,
|
|
"request_tps_mean": 18.258369295759792,
|
|
"request_tps_p50": 12.924863350205007,
|
|
"request_tps_p95": 36.94528376333951,
|
|
"aggregate_output_tps_mean": 33.27170984729996,
|
|
"aggregate_output_tps_p50": 33.918007597024484,
|
|
"aggregate_output_tps_p95": 35.45560236969114
|
|
}
|
|
] |