mindef-overdracht/llm-throughput-tests-mindef-metadateren/results/results_QuantTrio_Qwen3_5-35B-A3B-AWQ/benchmark_results.json
2026-06-02 11:46:20 +02:00

630 lines
15 KiB
JSON

{
"timestamp": "2026-03-11T11:10:08.245541",
"model_name": "QuantTrio/Qwen3.5-35B-A3B-AWQ",
"results": [
{
"config": {
"input_tokens": 1000,
"output_tokens": 512,
"batch_size": 1,
"num_batches": 2,
"total_requests": 2,
"actual_input_tokens": 1140
},
"success_metrics": {
"success_rate": 100.0,
"successful_requests": 2,
"failed_requests": 0
},
"latency": {
"mean": 9.155,
"std": 5.968,
"min": 3.187,
"max": 15.123,
"p50": 9.155,
"p95": 14.526,
"p99": 15.003,
"ci_95_lower": 0.884,
"ci_95_upper": 17.426
},
"ttft": {
"mean": 9.155,
"std": 5.968,
"p50": 9.155,
"p90": 13.929
},
"tokens": {
"total_generated": 1024,
"content_tokens": 1024,
"reasoning_tokens": 0,
"avg_per_request": 512.0
},
"throughput": {
"concurrent_total_tps": 55.62,
"concurrent_content_tps": 55.62,
"requests_per_second": 0.11,
"actual_wall_time": 18.412,
"efficiency_percent": 57.18
},
"batch_metrics": {
"num_batches": 2,
"avg_batch_size": 1.0,
"avg_batch_throughput": 97.26,
"min_batch_throughput": 33.86,
"max_batch_throughput": 160.67
}
},
{
"config": {
"input_tokens": 1000,
"output_tokens": 512,
"batch_size": 8,
"num_batches": 2,
"total_requests": 16,
"actual_input_tokens": 1003
},
"success_metrics": {
"success_rate": 100.0,
"successful_requests": 16,
"failed_requests": 0
},
"latency": {
"mean": 8.081,
"std": 2.287,
"min": 5.772,
"max": 10.373,
"p50": 8.085,
"p95": 10.372,
"p99": 10.373,
"ci_95_lower": 6.961,
"ci_95_upper": 9.202
},
"ttft": {
"mean": 8.081,
"std": 2.287,
"p50": 8.085,
"p90": 10.37
},
"tokens": {
"total_generated": 8192,
"content_tokens": 8192,
"reasoning_tokens": 0,
"avg_per_request": 512.0
},
"throughput": {
"concurrent_total_tps": 503.04,
"concurrent_content_tps": 503.04,
"requests_per_second": 0.98,
"actual_wall_time": 16.285,
"efficiency_percent": 91.31
},
"batch_metrics": {
"num_batches": 2,
"avg_batch_size": 8.0,
"avg_batch_throughput": 549.93,
"min_batch_throughput": 394.83,
"max_batch_throughput": 705.03
}
},
{
"config": {
"input_tokens": 1000,
"output_tokens": 512,
"batch_size": 32,
"num_batches": 2,
"total_requests": 64,
"actual_input_tokens": 1028
},
"success_metrics": {
"success_rate": 100.0,
"successful_requests": 64,
"failed_requests": 0
},
"latency": {
"mean": 8.686,
"std": 0.017,
"min": 8.636,
"max": 8.732,
"p50": 8.688,
"p95": 8.71,
"p99": 8.721,
"ci_95_lower": 8.682,
"ci_95_upper": 8.691
},
"ttft": {
"mean": 8.595,
"std": 0.727,
"p50": 8.687,
"p90": 8.707
},
"tokens": {
"total_generated": 32768,
"content_tokens": 32768,
"reasoning_tokens": 0,
"avg_per_request": 512.0
},
"throughput": {
"concurrent_total_tps": 1865.45,
"concurrent_content_tps": 1865.45,
"requests_per_second": 3.64,
"actual_wall_time": 17.566,
"efficiency_percent": 98.9
},
"batch_metrics": {
"num_batches": 2,
"avg_batch_size": 32.0,
"avg_batch_throughput": 1876.54,
"min_batch_throughput": 1870.97,
"max_batch_throughput": 1882.11
}
},
{
"config": {
"input_tokens": 1000,
"output_tokens": 512,
"batch_size": 64,
"num_batches": 2,
"total_requests": 128,
"actual_input_tokens": 1028
},
"success_metrics": {
"success_rate": 100.0,
"successful_requests": 128,
"failed_requests": 0
},
"latency": {
"mean": 12.207,
"std": 0.04,
"min": 12.108,
"max": 12.283,
"p50": 12.211,
"p95": 12.263,
"p99": 12.273,
"ci_95_lower": 12.2,
"ci_95_upper": 12.214
},
"ttft": {
"mean": 12.044,
"std": 1.066,
"p50": 12.205,
"p90": 12.257
},
"tokens": {
"total_generated": 65536,
"content_tokens": 65536,
"reasoning_tokens": 0,
"avg_per_request": 512.0
},
"throughput": {
"concurrent_total_tps": 2654.48,
"concurrent_content_tps": 2654.48,
"requests_per_second": 5.18,
"actual_wall_time": 24.689,
"efficiency_percent": 98.89
},
"batch_metrics": {
"num_batches": 2,
"avg_batch_size": 64.0,
"avg_batch_throughput": 2665.65,
"min_batch_throughput": 2658.45,
"max_batch_throughput": 2672.85
}
},
{
"config": {
"input_tokens": 10000,
"output_tokens": 512,
"batch_size": 1,
"num_batches": 2,
"total_requests": 2,
"actual_input_tokens": 8871
},
"success_metrics": {
"success_rate": 100.0,
"successful_requests": 2,
"failed_requests": 0
},
"latency": {
"mean": 3.533,
"std": 0.026,
"min": 3.507,
"max": 3.559,
"p50": 3.533,
"p95": 3.557,
"p99": 3.559,
"ci_95_lower": 3.497,
"ci_95_upper": 3.569
},
"ttft": {
"mean": 3.533,
"std": 0.026,
"p50": 3.533,
"p90": 3.554
},
"tokens": {
"total_generated": 1024,
"content_tokens": 1024,
"reasoning_tokens": 0,
"avg_per_request": 512.0
},
"throughput": {
"concurrent_total_tps": 142.85,
"concurrent_content_tps": 142.85,
"requests_per_second": 0.28,
"actual_wall_time": 7.168,
"efficiency_percent": 98.57
},
"batch_metrics": {
"num_batches": 2,
"avg_batch_size": 1.0,
"avg_batch_throughput": 144.92,
"min_batch_throughput": 143.85,
"max_batch_throughput": 145.99
}
},
{
"config": {
"input_tokens": 10000,
"output_tokens": 512,
"batch_size": 8,
"num_batches": 2,
"total_requests": 16,
"actual_input_tokens": 8895
},
"success_metrics": {
"success_rate": 100.0,
"successful_requests": 16,
"failed_requests": 0
},
"latency": {
"mean": 7.325,
"std": 0.144,
"min": 7.142,
"max": 7.493,
"p50": 7.333,
"p95": 7.489,
"p99": 7.492,
"ci_95_lower": 7.254,
"ci_95_upper": 7.395
},
"ttft": {
"mean": 7.325,
"std": 0.144,
"p50": 7.333,
"p90": 7.487
},
"tokens": {
"total_generated": 8192,
"content_tokens": 8192,
"reasoning_tokens": 0,
"avg_per_request": 512.0
},
"throughput": {
"concurrent_total_tps": 550.76,
"concurrent_content_tps": 550.76,
"requests_per_second": 1.08,
"actual_wall_time": 14.874,
"efficiency_percent": 98.45
},
"batch_metrics": {
"num_batches": 2,
"avg_batch_size": 8.0,
"avg_batch_throughput": 554.82,
"min_batch_throughput": 543.43,
"max_batch_throughput": 566.21
}
},
{
"config": {
"input_tokens": 10000,
"output_tokens": 512,
"batch_size": 32,
"num_batches": 2,
"total_requests": 64,
"actual_input_tokens": 8842
},
"success_metrics": {
"success_rate": 100.0,
"successful_requests": 64,
"failed_requests": 0
},
"latency": {
"mean": 16.085,
"std": 2.082,
"min": 13.822,
"max": 18.383,
"p50": 16.109,
"p95": 18.273,
"p99": 18.329,
"ci_95_lower": 15.575,
"ci_95_upper": 16.595
},
"ttft": {
"mean": 15.996,
"std": 2.114,
"p50": 14.22,
"p90": 18.248
},
"tokens": {
"total_generated": 32768,
"content_tokens": 32768,
"reasoning_tokens": 0,
"avg_per_request": 512.0
},
"throughput": {
"concurrent_total_tps": 995.46,
"concurrent_content_tps": 995.46,
"requests_per_second": 1.94,
"actual_wall_time": 32.917,
"efficiency_percent": 96.09
},
"batch_metrics": {
"num_batches": 2,
"avg_batch_size": 32.0,
"avg_batch_throughput": 1015.38,
"min_batch_throughput": 885.0,
"max_batch_throughput": 1145.76
}
},
{
"config": {
"input_tokens": 10000,
"output_tokens": 512,
"batch_size": 64,
"num_batches": 2,
"total_requests": 128,
"actual_input_tokens": 8842
},
"success_metrics": {
"success_rate": 100.0,
"successful_requests": 128,
"failed_requests": 0
},
"latency": {
"mean": 14.781,
"std": 0.143,
"min": 14.277,
"max": 15.099,
"p50": 14.781,
"p95": 15.032,
"p99": 15.096,
"ci_95_lower": 14.756,
"ci_95_upper": 14.806
},
"ttft": {
"mean": 14.781,
"std": 0.143,
"p50": 14.781,
"p90": 14.972
},
"tokens": {
"total_generated": 65536,
"content_tokens": 65536,
"reasoning_tokens": 0,
"avg_per_request": 512.0
},
"throughput": {
"concurrent_total_tps": 2166.53,
"concurrent_content_tps": 2166.53,
"requests_per_second": 4.23,
"actual_wall_time": 30.249,
"efficiency_percent": 97.72
},
"batch_metrics": {
"num_batches": 2,
"avg_batch_size": 64.0,
"avg_batch_throughput": 2174.01,
"min_batch_throughput": 2164.24,
"max_batch_throughput": 2183.78
}
},
{
"config": {
"input_tokens": 50000,
"output_tokens": 512,
"batch_size": 1,
"num_batches": 2,
"total_requests": 2,
"actual_input_tokens": 42229
},
"success_metrics": {
"success_rate": 100.0,
"successful_requests": 2,
"failed_requests": 0
},
"latency": {
"mean": 6.101,
"std": 0.019,
"min": 6.082,
"max": 6.12,
"p50": 6.101,
"p95": 6.118,
"p99": 6.12,
"ci_95_lower": 6.074,
"ci_95_upper": 6.128
},
"ttft": {
"mean": 6.101,
"std": 0.019,
"p50": 6.101,
"p90": 6.117
},
"tokens": {
"total_generated": 1024,
"content_tokens": 1024,
"reasoning_tokens": 0,
"avg_per_request": 512.0
},
"throughput": {
"concurrent_total_tps": 83.22,
"concurrent_content_tps": 83.22,
"requests_per_second": 0.16,
"actual_wall_time": 12.305,
"efficiency_percent": 99.16
},
"batch_metrics": {
"num_batches": 2,
"avg_batch_size": 1.0,
"avg_batch_throughput": 83.92,
"min_batch_throughput": 83.66,
"max_batch_throughput": 84.19
}
},
{
"config": {
"input_tokens": 50000,
"output_tokens": 512,
"batch_size": 8,
"num_batches": 2,
"total_requests": 16,
"actual_input_tokens": 42048
},
"success_metrics": {
"success_rate": 100.0,
"successful_requests": 16,
"failed_requests": 0
},
"latency": {
"mean": 22.685,
"std": 2.474,
"min": 20.003,
"max": 25.463,
"p50": 22.588,
"p95": 25.387,
"p99": 25.448,
"ci_95_lower": 21.473,
"ci_95_upper": 23.897
},
"ttft": {
"mean": 22.685,
"std": 2.474,
"p50": 22.588,
"p90": 25.295
},
"tokens": {
"total_generated": 8192,
"content_tokens": 8192,
"reasoning_tokens": 0,
"avg_per_request": 512.0
},
"throughput": {
"concurrent_total_tps": 177.76,
"concurrent_content_tps": 177.76,
"requests_per_second": 0.35,
"actual_wall_time": 46.085,
"efficiency_percent": 97.28
},
"batch_metrics": {
"num_batches": 2,
"avg_batch_size": 8.0,
"avg_batch_throughput": 180.32,
"min_batch_throughput": 160.6,
"max_batch_throughput": 200.04
}
},
{
"config": {
"input_tokens": 50000,
"output_tokens": 512,
"batch_size": 32,
"num_batches": 2,
"total_requests": 64,
"actual_input_tokens": 41752
},
"success_metrics": {
"success_rate": 100.0,
"successful_requests": 64,
"failed_requests": 0
},
"latency": {
"mean": 70.626,
"std": 18.722,
"min": 48.439,
"max": 90.756,
"p50": 70.358,
"p95": 90.447,
"p99": 90.677,
"ci_95_lower": 66.039,
"ci_95_upper": 75.213
},
"ttft": {
"mean": 70.626,
"std": 18.722,
"p50": 70.358,
"p90": 90.064
},
"tokens": {
"total_generated": 32768,
"content_tokens": 32768,
"reasoning_tokens": 0,
"avg_per_request": 512.0
},
"throughput": {
"concurrent_total_tps": 225.4,
"concurrent_content_tps": 225.4,
"requests_per_second": 0.44,
"actual_wall_time": 145.377,
"efficiency_percent": 90.31
},
"batch_metrics": {
"num_batches": 2,
"avg_batch_size": 32.0,
"avg_batch_throughput": 241.37,
"min_batch_throughput": 179.6,
"max_batch_throughput": 303.14
}
},
{
"config": {
"input_tokens": 50000,
"output_tokens": 512,
"batch_size": 64,
"num_batches": 2,
"total_requests": 128,
"actual_input_tokens": 41810
},
"success_metrics": {
"success_rate": 63.28,
"successful_requests": 81,
"failed_requests": 47
},
"latency": {
"mean": 111.228,
"std": 2.973,
"min": 106.149,
"max": 115.385,
"p50": 112.37,
"p95": 114.998,
"p99": 115.289,
"ci_95_lower": 110.581,
"ci_95_upper": 111.876
},
"ttft": {
"mean": 111.228,
"std": 2.973,
"p50": 112.37,
"p90": 114.818
},
"tokens": {
"total_generated": 41472,
"content_tokens": 41472,
"reasoning_tokens": 0,
"avg_per_request": 512.0
},
"throughput": {
"concurrent_total_tps": 182.43,
"concurrent_content_tps": 182.43,
"requests_per_second": 0.36,
"actual_wall_time": 227.333,
"efficiency_percent": 61.88
},
"batch_metrics": {
"num_batches": 2,
"avg_batch_size": 40.5,
"avg_batch_throughput": 181.97,
"min_batch_throughput": 162.11,
"max_batch_throughput": 201.84
}
}
]
}