YOLOv8n on Hailo-8L: 2 rows.
Method v1.0 · dataset 2026-09-07 · verified 2026-09-07 · last updated September 2026
yolov8n on Hailo-8L: 2 rows (2 measured, 0 derived). Expected: INT8 53–65 fps. Fastest: NVIDIA A100 (server) 1010.1 fps (class C), Jetson Thor T5000 859 fps (class D), NVIDIA L4 (24GB) 816 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 |
|---|---|---|---|---|---|---|---|
| INT8 | fps | 2 | 53 | 59 | 65 | C | 2 |
Rows
| Precision | Runtime | Input | Power mode | Software | Metric | Class | Date | Source | Derivation | Dupes |
|---|---|---|---|---|---|---|---|---|---|---|
| INT8 | hailo sdk (inferred) | 640x640 b1 | default | — | 65 fps | C | 2024-Q2 | Hailo (community examples) · github:hailo-ai/hailo-rpi5-examples · verified 2026-09-07 | 1 | |
| INT8 | hailo sdk (inferred) | 640x640 b8 | default | — | 53 fps | C | 2024-Q1 | Hailo · github:hailo-ai/hailo_model_zoo/HAILO8L_object_detection · verified 2026-09-07 | 1 |
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) | 1010.1 fps | C |
| Jetson Thor T5000 | 859 fps | D |
| NVIDIA L4 (24GB) | 816 fps | D |
| NVIDIA A10 (24GB) | 594 fps | D |
| Jetson AGX Orin 64GB | 504 fps | D |
| Hailo-10H | 378 fps | D |
| Jetson AGX Orin 32GB | 352 fps | D |
| NVIDIA A2 (16GB) | 352 fps | D |
| Jetson Orin Nano Super | 341 fps | D |
| Jetson Orin NX 16GB | 264 fps | D |
| Jetson Orin NX 8GB | 160 fps | D |
| Hailo-8 | 107 fps | C |
| Hailo-8L | 65 fps | C |
| Rockchip RK3588 NPU | 61 fps | D |
| Jetson Orin Nano 8GB | 48 fps | D |
| Neousys Nuvo-9531 (Intel 12th-14th Gen Core) | 28 fps | D |
| Raspberry Pi 5 (CPU) (reference) | 12.4 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.
- 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_8l&model=yolov8&variant=n&mv=1.0&dv=2026-09-07
- Methodology: /methodology/benchmark-explorer/
- Measurement protocol: /methodology/measurement-protocol/
- Dataset: /datasets/benchmarks-v2.json
- Hailo-8L overview: /benchmarks/hailo-8l/
Change one input and re-run.
The live engine keeps every source line and gives you a fresh permalink and summary.