YOLO11m on NVIDIA A2 (16GB): 1 row.
Method v1.0 · dataset 2026-09-07 · verified 2026-09-07 · last updated September 2026
yolo11m on NVIDIA A2 (16GB): 1 row (0 measured, 1 derived). Expected: FP16 152 fps. Fastest: NVIDIA L40S (48GB) 921 fps (class D), Jetson Thor T5000 470 fps (class D), NVIDIA L4 (24GB) 288 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 | 152 | 152 | 152 | D | 0 |
Rows
| Precision | Runtime | Input | Power mode | Software | Metric | Class | Date | Source | Derivation | Dupes |
|---|---|---|---|---|---|---|---|---|---|---|
| FP16 | tensorrt | 640x640 b1 | default | sdk v1 | 152 fps | D | 2026 | EdgeAIStack · edgeaistack:benchmark-corpus · Server Inference Capacity · verified 2026-09-07 | Server Inference Capacity | 0 |
Cross-hardware comparison
Best row per hardware for the same model and precision, relative to the fastest.
| Hardware | Best value | Class |
|---|---|---|
| NVIDIA L40S (48GB) | 921 fps | D |
| Jetson Thor T5000 | 470 fps | D |
| NVIDIA L4 (24GB) | 288 fps | D |
| NVIDIA A10 (24GB) | 224 fps | D |
| Jetson AGX Orin 64GB | 213 fps | C |
| NVIDIA T4 (server) (reference) | 212.8 fps | C |
| NVIDIA A2 (16GB) | 152 fps | D |
| Jetson Orin Nano Super | 110 fps | C |
| Jetson Orin NX 16GB | 103 fps | C |
| Jetson AGX Orin 32GB | 73.4 fps | D |
| Hailo-10H | 70.3 fps | D |
| Hailo-8 | 55 fps | C |
| Jetson Orin NX 8GB | 53.1 fps | D |
| Hailo-8L | 35.3 fps | D |
| Jetson Orin Nano 8GB | 31.4 fps | D |
| Rockchip RK3588 NPU | 16.9 fps | D |
| Neousys Nuvo-9531 (Intel 12th-14th Gen Core) | 6 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.
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=nvidia_a2_server&model=yolo11&variant=m&mv=1.0&dv=2026-09-07
- Methodology: /methodology/benchmark-explorer/
- Measurement protocol: /methodology/measurement-protocol/
- Dataset: /datasets/benchmarks-v2.json
- NVIDIA A2 (16GB) overview: /benchmarks/nvidia-a2-server/
Change one input and re-run.
The live engine keeps every source line and gives you a fresh permalink and summary.