YOLO11n on Jetson Orin Nano Super: 1 row.
Method v1.4.1 · dataset 2026-09-16 · verified 2026-09-16 · last updated September 2026
yolo11_segn on Jetson Orin Nano Super: 1 row (1 measured, 0 derived). Measured share for this scope: 67% of 63 rows (class C). Expected: FP16 186.1 fps. Fastest: Jetson Thor T5000 530 fps (class C), Jetson AGX Orin 64GB 365.51 fps (class C), Jetson Orin Nano Super 186.1 fps (class C).
Change hardware, precision, runtime or add a comparison set on the live engine.
Expected range per precision
Min / median / max of the matching rows, all classes. When a precision has no row, the estimator's benchmark hierarchy (B → C → D) supplies a fallback with its tier chain reported.
| Precision | Metric | N | Min | Median | Max | Best class | Measured |
|---|---|---|---|---|---|---|---|
| FP16 | fps | 1 | 186.1 | 186.1 | 186.1 | C | 1 |
Rows
| Precision | Runtime | Input | Power mode | Software | Metric | Class | Date | Source | Derivation | Dupes |
|---|---|---|---|---|---|---|---|---|---|---|
| FP16 | tensorrt | 640x640 b1 | — | tensorrt 10.3.0 | 186.1 fps | C | 2026 | EdgeFirst AI · bench:edgefirst-yolo-validator-benchmarks-jetson-orin-nano-super-tensorrt-metrics 2026-06-22 · Ultralytics validator lane, latency_ms.inf · verified 2026-09-28 | 0 |
Cross-hardware comparison
Best row per hardware for the same model and precision, relative to the fastest.
| Hardware | Best value | Class |
|---|---|---|
| Jetson Thor T5000 | 530 fps | C |
| Jetson AGX Orin 64GB | 365.51 fps | C |
| Jetson Orin Nano Super | 186.1 fps | C |
| Hailo-8 | 130 fps | D |
| Hailo-8L | 129 fps | D |
| Rockchip RK3588 NPU | 49.8 fps | C |
| Neousys Nuvo-9531 (Intel 12th-14th Gen Core) | 15 fps | D |
Assumptions
- Latency provenance: 0 of the 1 matching rows that report a latency computed it as 1000/fps rather than measuring it (latency_source → derived_reciprocal); 1 was observed independently. Every p99 in the database is a modelled 1.20–1.43× tail over the p50, never an observed one.
- Class C = measured and published by the source named on the row; class D = EdgeAIStack-derived (derivation stated). Rows are inference-only unless scope says end_to_end; publisher measurement conditions (JetPack, batch, warm-up) are in the linked page.
Method and limitations
Rows are read from the normalised benchmark database (publisher benchmarks and research-derived rows, deduplicated per hardware × model × runtime × precision × input × power mode, best evidence kept). Expected range = min / median / max of the matching rows per precision; when a precision has no row the estimator's benchmark hierarchy (B → C → D) is consulted and its tier chain reported. Comparison = best row per hardware for the same model and precision, relative to the fastest. Nothing is scored; every number carries its class and source line.
Full method, dedupe rule, evidence classes and the confidence rule: Benchmark Explorer methodology.
Measure it yourself.
Nothing measured for your exact config, or want to confirm a class-D row? Run the measurement protocol on your board and submit the result — a human checks it against the protocol before it becomes a class-C row with your attribution.
Links
- Live engine (this exact query): https://edgeaistack.ai/engines/benchmark-explorer/?hw=jetson_orin_nano_super&model=yolo11_seg&variant=n&mv=1.4.1&dv=2026-09-16
- Methodology: /methodology/benchmark-explorer/
- Measurement protocol: /methodology/measurement-protocol/
- Dataset: /datasets/benchmarks-v2.json
- Platform page: Jetson Orin Nano Super
- Jetson Orin Nano Super overview: /benchmarks/jetson-orin-nano-super/
Change one input and re-run.
The live engine keeps every source line and gives you a fresh permalink and summary.