Skip to navigation

Performance Results

View as MarkdownOpen in Claude

The NVIDIA Active Speaker Detection NIM supports multiple concurrent inputs per GPU. The following performance data is representative and intended to give a general idea of performance expectations. Actual results might vary depending on hardware configuration, input characteristics, and workload. The table shows performance data for various concurrency levels on various GPUs with different sample inputs.

GPUSpeaker CountConcurrencyAverage FPS
RTX L40S1172
1258
1429
1818
2175
2253
2429
2819
3173
3256
3433
3817
RTX A10g1158
1244
1422
1813
2160
2241
2426
2813
3154
3233
3418
3811
RTX 40901172
1249
1428
1820
2177
2253
2431
2823
3173
3246
3426
3821
RTX 50901169
1254
1426
1816
2173
2250
2430
2817
3170
3253
3426
3815

The inference FPS is calculated by dividing the total number of frames in input video file by the total inference time in seconds (measured from the time the request is sent until complete output file is received by the client).

Note: Video extension operations significantly increase processing time and memory usage due to frame buffering.

For more information, refer to the Maxine NIM clients Github repository: NVIDIA-Maxine/nim-clients.