Kria KV260 vs Jetson Orin Nano Super: which is faster?
The NVIDIA Jetson Orin Nano Super is faster in every one of the 2 matched comparisons we have. For example, on object detection (nano models, batch 1) the NVIDIA Jetson Orin Nano Super runs 263 FPS against 33.6 FPS.
| Workload · group | AMD Kria KV260 Vision AI Starter Kit (K26 SOM) | NVIDIA Jetson Orin Nano Super | Faster |
|---|---|---|---|
| object detection nano (YOLO-n) · batch 1 | 33.60 FPS C 2025-11-17 (published) YOLOv8n-Ghost (Hard-Swish, xView3-SAR) · arXiv 2507.04842v2 (SAR vessel detection on Kria KV260), Table 6 | 263 FPS B 2026-10-13 (page last edited) YOLO26n · Ultralytics documentation (benchmark table) | NVIDIA Jetson Orin Nano Super (7.83×) |
| object detection small (YOLO-s) · batch 1 | 12.20 FPS C 2025-11-17 (published) YOLOv8s-Ghost-P2 (Hard-Swish, xView3-SAR) · arXiv 2507.04842v2 (SAR vessel detection on Kria KV260), Table 6 | 146 FPS C 2026-08-02 (published) YOLO11s (640x640) · arXiv 2608.00927 AgriJetsonBench (abstract figures) | NVIDIA Jetson Orin Nano Super (11.95×) |
Sources
- https://docs.ultralytics.com/guides/nvidia-jetson/
- https://arxiv.org/abs/2507.04842v2
- https://arxiv.org/abs/2608.00927
Generated 2026-10-16 from HWBench data only. All answers · Submit a result
Machine-readable: /find.json (see llms.txt); full tables are in “Show data”. Confidence grades: A audited MLPerf closed · B documented third-party · C community · D vendor-published · E estimate. Unknown values are shown as unknown, never estimated. Generated 2026-10-16 from public sources.