Profile Job Results
Jobs
j5mmr39y5
Results Ready
Name
mobile_facenet
Target Device
- SA7255P ADP
- Android 14
- Qualcomm® SA7255P
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
img1: float32[1, 3, 112, 112]img2: float32[1, 3, 112, 112]Completion Time
9/6/2026, 1:25:38 AM
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-2026.08.28.1
Estimated Inference Time
4.45 ms
Estimated Peak Memory Usage
0 ‑ 32 MB
Compute Units
NPU
84
| Stage | Time | Memory |
|---|---|---|
First App Load | 2.83 s | 25‑30 MB |
Subsequent App Load | 537 ms | 3‑37 MB |
Inference | 4.45 ms | 0‑32 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 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device