Profile Job Results
Jobs
jp4y812lp
Results Ready
Name
mobile_facenet
Target Device
- Samsung Galaxy S24
- Android 14
- Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
img1: float32[1, 3, 112, 112]img2: float32[1, 3, 112, 112]Completion Time
9/19/2026, 8:28:16 PM
Options
--qairt_version latestVersions
- Lite RT: 1.4.2
- QAIRT: v2.50.0.260828221209
- QNN TfLite Delegate: v2.50.0.260828221209
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.09.11.0
Estimated Inference Time
699 μs
Estimated Peak Memory Usage
9 ‑ 60 MB
Compute Units
NPU
84
| Stage | Time | Memory |
|---|---|---|
First App Load | 778 ms | 85‑91 MB |
Subsequent App Load | 156 ms | 0‑54 MB |
Inference | 699 μs | 9‑60 MB |
| Lite RT | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.performance_mode | kHtpBurst |
| 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