YOLOv10s on Hailo-10H: 2 rows.
Method v1.2 · dataset 2026-09-16 · verified 2026-09-16 · last updated September 2026
yolov10s on Hailo-10H: 2 rows (2 measured, 0 derived). Expected: INT8 146–230 fps. Fastest: NVIDIA T4 (server) 401.6 fps (class C), Hailo-8 283 fps (class C), Hailo-10H 230 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 |
|---|---|---|---|---|---|---|---|
| INT8 | fps | 2 | 146 | 188 | 230 | C | 2 |
range pools 2 rows across batch; not one measurement condition | |||||||
Rows
| Precision | Runtime | Input | Power mode | Software | Metric | Class | Date | Source | Derivation | Dupes |
|---|---|---|---|---|---|---|---|---|---|---|
| INT8 | hailo sdk | 640x640 b8 | — | hailo_dataflow_compiler v5.4.0 | 230 fps | C | 2026 | Hailo · bench:hailo-hailo-model-zoo-object-detection-benchmarks · verified 2026-09-16 | 0 | |
| INT8 | hailo sdk | 640x640 b1 | — | hailo_dataflow_compiler v5.4.0 | 146 fps | C | 2026 | Hailo · bench:hailo-hailo-model-zoo-object-detection-benchmarks · verified 2026-09-16 | 0 |
Cross-hardware comparison
Best row per hardware for the same model and precision, relative to the fastest.
| Hardware | Best value | Class |
|---|---|---|
| NVIDIA T4 (server) (reference) | 401.6 fps | C |
| Hailo-8 | 283 fps | C |
| Hailo-10H | 230 fps | C |
| Hailo-8L | 187 fps | C |
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=hailo_10h&model=yolov10&variant=s&mv=1.2&dv=2026-09-16
- Methodology: /methodology/benchmark-explorer/
- Measurement protocol: /methodology/measurement-protocol/
- Dataset: /datasets/benchmarks-v2.json
- Hailo-10H overview: /benchmarks/hailo-10h/
Change one input and re-run.
The live engine keeps every source line and gives you a fresh permalink and summary.