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

**URL:** <https://community.ultralytics.com/t/yolo11-or-yolo26-for-jetson-orin-nx-16gb-with-a-custom-dataset/2145>\
**Category:** YOLO\
**Tags:** yolo, support\
**Created:** [July 30, 2026, 10:32am UTC](https://community.ultralytics.com/t/yolo11-or-yolo26-for-jetson-orin-nx-16gb-with-a-custom-dataset/2145 "2026-07-30T10:32:02Z")\
**Posts on this page:** 6\
**Page:** 1

<div class="post-metadata">

**Author:** ![Ahmad\_Khan](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/ahmad_khan/32/1633_2.png) [@Ahmad\_Khan](https://community.ultralytics.com/u/Ahmad_Khan)\
**Post date:** [July 30, 2026, 10:32am UTC](https://community.ultralytics.com/t/yolo11-or-yolo26-for-jetson-orin-nx-16gb-with-a-custom-dataset/2145/1 "2026-07-30T10:32:02Z")

</div>

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!

---

<div class="post-metadata">

**Author:** ![Toxite](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/toxite/32/123_2.png) [@Toxite](https://community.ultralytics.com/u/Toxite)\
**Post date:** [July 30, 2026, 10:34am UTC](https://community.ultralytics.com/t/yolo11-or-yolo26-for-jetson-orin-nx-16gb-with-a-custom-dataset/2145/2 "2026-07-30T10:34:20Z")

</div>

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

> **[Detailed Comparison Tables - YOLO26 on NVIDIA Jetson Setup & Benchmarks |...](https://docs.ultralytics.com/guides/nvidia-jetson#detailed-comparison-tables)**
>
> This comprehensive guide provides a detailed walkthrough for deploying Ultralytics YOLO26 on NVIDIA Jetson devices. Additionally, it showcases performance benchmarks to demonstrate the capabilities of YOLO26 on these small and powerful devices. |...

---

<div class="post-metadata">

**Author:** ![Ahmad\_Khan](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/ahmad_khan/32/1633_2.png) [@Ahmad\_Khan](https://community.ultralytics.com/u/Ahmad_Khan)\
**Post date:** [July 31, 2026, 4:13am UTC](https://community.ultralytics.com/t/yolo11-or-yolo26-for-jetson-orin-nx-16gb-with-a-custom-dataset/2145/3 "2026-07-31T04:13:03Z")

</div>

Thank you!

---

<div class="post-metadata">

**Author:** ![pderrenger](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/pderrenger/32/73_2.png) [@pderrenger](https://community.ultralytics.com/u/pderrenger)\
**Post date:** [August 1, 2026, 12:57am UTC](https://community.ultralytics.com/t/yolo11-or-yolo26-for-jetson-orin-nx-16gb-with-a-custom-dataset/2145/4 "2026-08-01T00:57:32Z")

</div>

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.

---

<div class="post-metadata">

**Author:** ![Ahmad\_Khan](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/ahmad_khan/32/1633_2.png) [@Ahmad\_Khan](https://community.ultralytics.com/u/Ahmad_Khan)\
**Post date:** [August 1, 2026, 5:36am UTC](https://community.ultralytics.com/t/yolo11-or-yolo26-for-jetson-orin-nx-16gb-with-a-custom-dataset/2145/5 "2026-08-01T05:36:47Z")

</div>

**Okay, thanks!**

###

---

<div class="post-metadata">

**Author:** ![pderrenger](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/pderrenger/32/73_2.png) [@pderrenger](https://community.ultralytics.com/u/pderrenger)\
**Post date:** [August 2, 2026, 12:58am UTC](https://community.ultralytics.com/t/yolo11-or-yolo26-for-jetson-orin-nx-16gb-with-a-custom-dataset/2145/6 "2026-08-02T00:58:11Z")

</div>

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