Profile Job Results
Jobs
j5w3v63jp
Results Ready
Name
bisenet
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 3, 720, 960]Completion Time
9/28/2025, 3:54:22 AM
Options
--qairt_version 2.37Versions
- ONNX Runtime: 1.22.2
- QAIRT: v2.37.1.250807093845_124904
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.09.23.1
Estimated Inference Time
33.3 ms
Estimated Peak Memory Usage
71 ‑ 92 MB
Compute Units
NPU
82
| Stage | Time | Memory |
|---|---|---|
First App Load | 3.87 s | 259‑260 MB |
Subsequent App Load | 3.93 s | 315‑317 MB |
Inference | 33.3 ms | 71‑92 MB |
| ONNX Runtime | Value |
|---|---|
| execution_mode | SEQUENTIAL |
| intra_op_num_threads | 0 |
| inter_op_num_threads | 0 |
| enable_memory_pattern | false |
| enable_cpu_memory_arena | false |
| graph_optimization_level | ENABLE_ALL |
| QNN Execution Provider | Value |
|---|---|
| htp_performance_mode | "burst" |
| htp_graph_finalization_optimization_mode | "3" |
| enable_htp_fp16_precision | "1" |
| capture_network_visualizations | false |
Sign up to run this model on a hosted Qualcomm® device!
Run on device