YOLO11x on Jetson AGX Orin 64GB: 3 rows.
Method v1.0 · dataset 2026-09-07 · verified 2026-09-07 · last updated September 2026
yolo11x on Jetson AGX Orin 64GB: 3 rows (3 measured, 0 derived). Expected: FP16 74 fps; FP32 17 fps; INT8 106 fps. Fastest: Jetson Thor T5000 218 fps (class D), Jetson AGX Orin 64GB 106 fps (class C), NVIDIA T4 (server) 88.5 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 | 74 | 74 | 74 | C | 1 |
| FP32 | fps | 1 | 17 | 17 | 17 | C | 1 |
| INT8 | fps | 1 | 106 | 106 | 106 | C | 1 |
Rows
| Precision | Runtime | Input | Power mode | Software | Metric | Class | Date | Source | Derivation | Dupes |
|---|---|---|---|---|---|---|---|---|---|---|
| INT8 | tensorrt | 640x640 b1 | 60w | ultralytics 8.3.157 | 106 fps | C | 2024 | Ultralytics · bench:ultralytics-yolo11-jetson 8.3.157 · verified 2026-09-07 | 1 | |
| FP16 | tensorrt | 640x640 b1 | 60w | ultralytics 8.3.157 | 74 fps | C | 2024 | Ultralytics · bench:ultralytics-yolo11-jetson 8.3.157 · verified 2026-09-07 | 1 | |
| FP32 | pytorch | 640x640 b1 | 60w | ultralytics 8.3.157 | 17 fps | C | 2024 | Ultralytics · bench:ultralytics-yolo11-jetson 8.3.157 · verified 2026-09-07 | 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 | 218 fps | D |
| Jetson AGX Orin 64GB | 106 fps | C |
| NVIDIA T4 (server) (reference) | 88.5 fps | C |
| Jetson Orin Nano Super | 50 fps | C |
| Jetson Orin NX 16GB | 46 fps | C |
| Hailo-8 | 14.2 fps | D |
| Hailo-8L | 12.1 fps | D |
| Rockchip RK3588 NPU | 6.4 fps | D |
| Neousys Nuvo-9531 (Intel 12th-14th Gen Core) | 1.8 fps | D |
Assumptions
- 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_agx_orin&model=yolo11&variant=x&mv=1.0&dv=2026-09-07
- Methodology: /methodology/benchmark-explorer/
- Measurement protocol: /methodology/measurement-protocol/
- Dataset: /datasets/benchmarks-v2.json
- Platform page: Jetson AGX Orin 64GB
- Jetson AGX Orin 64GB overview: /benchmarks/jetson-agx-orin/
Change one input and re-run.
The live engine keeps every source line and gives you a fresh permalink and summary.