> This page is for version 0.2.0 (Latest) (default).
> For other versions, use one of these documentation indexes:
> - 0.2.0 (Latest) (default): https://docs.nvidia.com/nim/computer-vision/semantic-split/0.2.0/llms.txt
> - 0.1.0: https://docs.nvidia.com/nim/computer-vision/semantic-split/0.1.0/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nim/computer-vision/semantic-split/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nim/computer-vision/semantic-split/_mcp/server.

# Performance

Performance of the Semantic Split C-RADIO NIM is measured in throughput, where throughput is defined as the number of frames processed in a given duration for a video split request. Both the NIM and client share the same computer to minimize network latency. The performance is averaged across three different runs.

| GPU | Input Source | Results Destination | Video Resolution | Input Codec | Number of Videos | Duration of Videos | Throughput (Frames/second) |
| --- | --- | --- | --- | --- | --- | --- | --- |
| L40S | Local file System | Local file System | 1280x720 | H264 | 84 | (Minimum, Average, Maximum) - (1.98, 4.74, 8.17) | 4800 |
| L20 | Local file System | Local file System | 1280x720 | H264 | 84 | (Minimum, Average, Maximum) - (1.98, 4.74, 8.17) | 4900 |