YOLOv8x on Jetson AGX Orin 64GB: 2 rows.
Method v1.4.1 · dataset 2026-09-29 · verified 2026-09-16 · last updated September 2026
yolov8x on Jetson AGX Orin 64GB: 2 rows (2 measured, 0 derived). Measured share for this scope: 53% of 64 rows (class C). Expected: FP16 67 fps; INT8 107 fps. Fastest: NVIDIA A100 (server) 283.3 fps (class C), Jetson AGX Orin 64GB 107 fps (class C), Jetson AGX Orin 32GB 85 fps (class D).
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 | 67 | 67 | 67 | C | 1 |
| INT8 | fps | 1 | 107 | 107 | 107 | C | 1 |
Rows
| Precision | Runtime | Input | Power mode | Software | Metric | Class | Date | Source | Derivation | Dupes |
|---|---|---|---|---|---|---|---|---|---|---|
| INT8 | tensorrt | 640x640 b1 | maxn | — | 107 fps | C | 2026 | Ultralytics Inc. · bench:ultralytics-inc-https-docs-ultralytics-com-guides-nvidia-jetson-benchmark-results · verified 2026-09-16 | 0 | |
| FP16 | tensorrt | 640x640 b1 | maxn | — | 67 fps | C | 2026 | Ultralytics Inc. · bench:ultralytics-inc-https-docs-ultralytics-com-guides-nvidia-jetson-benchmark-results · verified 2026-09-16 | 2 |
Cross-hardware comparison
Best row per hardware for the same model and precision, relative to the fastest.
| Hardware | Best value | Class |
|---|---|---|
| NVIDIA A100 (server) (reference) | 283.3 fps | C |
| Jetson AGX Orin 64GB | 107 fps | C |
| Jetson AGX Orin 32GB | 85 fps | D |
| Jetson Orin Nano Super | 44 fps | C |
| Hailo-10H | 25.6 fps | D |
| Jetson Orin NX 16GB | 20 fps | C |
| Hailo-8 | 18 fps | D |
| Hailo-8L | 16.2 fps | D |
| Neousys Nuvo-9531 (Intel 12th-14th Gen Core) | 2 fps | D |
Assumptions
- Latency provenance: 2 of the 2 matching rows that report a latency computed it as 1000/fps rather than measuring it (latency_source → derived_reciprocal); 0 were 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_agx_orin&model=yolov8&variant=x&mv=1.4.1&dv=2026-09-29
- 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.