YOLO11 or YOLO26 for Jetson Orin NX 16GB with a custom dataset

Support YOLO
,
1

Hello everyone,

I’m using a Jetson Orin NX 16GB with a custom dataset, deployed with DeepStream, TensorRT, and INT8. Which model do you recommend, YOLO11 or YOLO26, and which size (l or x)?

Thanks!

2

You can try YOLO26l. We have speed benchmarks on our docs for different model sizes:

3

Thank you!

4

You’re welcome! Benchmark the final INT8 engine in your actual DeepStream pipeline, as input resolution, stream count, preprocessing, and tracking can significantly affect end-to-end performance. If you encounter issues, share your JetPack, TensorRT, DeepStream, and Ultralytics versions along with the logs.

5

Okay, thanks!

6

You’re welcome! Good luck with the deployment, and feel free to share your results or any issues you encounter.