Profile Job Results
Jobs
jg9dze485
Results Ready
Name
fcn_resnet50
Target Device
- SA8775P ADP
- Android 14
- Qualcomm® SA8775P
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: float32[1, 520, 520, 3]Completion Time
8/8/2026, 3:48:17 PM
Versions
- Lite RT: 1.4.5
- QAIRT: v2.45.0.260326154327
- QNN TfLite Delegate: v2.45.0.260326154327
- Android: 14 (UAG2.240908.001)
- Build ID: Snapdragon_Auto.HQX.4.5.6.0.r2-00016-STD.PROD-3
- AI Hub: aihub-2026.07.31.1
Estimated Inference Time
72.9 ms
Estimated Peak Memory Usage
0 ‑ 354 MB
Compute Units
NPU
80
| Stage | Time | Memory |
|---|---|---|
First App Load | 32.5 s | 350‑355 MB |
Subsequent App Load | 552 ms | 68‑422 MB |
Inference | 72.9 ms | 0‑354 MB |
| Lite RT | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.precision | kHtpFp16 |
| htp_options.optimization_strategy | kHtpOptimizeForInferenceO3 |
| htp_options.useConvHmx | true |
| htp_options.device_id | 1 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device