Profile Job Results
Jobs
jp02xr795
Results Ready
Name
swin_tiny
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_tensor: uint16[1, 3, 224, 224]Completion Time
9/13/2025, 10:40:43 PM
Options
--qairt_version 2.36Versions
- ONNX Runtime: 1.22.2
- QAIRT: v2.36.4.250725200057_123280
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2025.09.05.0
Estimated Inference Time
58.5 ms
Estimated Peak Memory Usage
133 ‑ 234 MB
Compute Units
NPU
999
CPU
37
| Stage | Time | Memory |
|---|---|---|
First App Load | 20.5 s | 287‑288 MB |
Subsequent App Load | 22.5 s | 280‑283 MB |
Inference | 58.5 ms | 133‑234 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