YOLOv9t on Jetson Orin NX 16GB: 1 row.
Method v1.4.1 · dataset 2026-09-29 · verified 2026-09-16 · last updated September 2026
yolov9t on Jetson Orin NX 16GB: 1 row (0 measured, 1 derived). Measured share for this scope: 44% of 50 rows (class C). Expected: FP16 195 fps.
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 | 195 | 195 | 195 | D | 0 |
Rows
| Precision | Runtime | Input | Power mode | Software | Metric | Class | Date | Source | Derivation | Dupes |
|---|---|---|---|---|---|---|---|---|---|---|
| FP16 | tensorrt (inferred) | 640x640 b1 | — | — | 195 fps · ≈6.2 ms p99 (derived p99) | D | 2024-Q1 | EdgeAIStack · edgeaistack:benchmark-corpus · corpus record yolov9t-orin-nx-estimated-fp16-085 · verified 2026-09-16 | EdgeAIStack estimate — corpus record yolov9t-orin-nx-estimated-fp16-085 | 0 |
Cross-hardware comparison
Best row per hardware for the same model and precision, relative to the fastest.
| Hardware | Best value | Class |
|---|---|---|
| Jetson Orin NX 16GB | 195 fps | D |
Assumptions
- Rows from the research corpus do not state a runtime; the platform's native runtime (TensorRT / Edge TPU / Hailo SDK / RKNN / CPU) is assumed and flagged runtime_inferred.
- Latency provenance: 1 of the 1 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.
Warnings
- 1 of 1 matching rows are EdgeAIStack-derived (class D); treat them as estimates until a measured row (class C) or your own measurement replaces them.
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_nx&model=yolov9&variant=t&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 Orin NX 16GB
- Jetson Orin NX 16GB overview: /benchmarks/jetson-orin-nx/
Change one input and re-run.
The live engine keeps every source line and gives you a fresh permalink and summary.