Profile Job Results
Jobs
j57vy9095
Results Ready
Name
face_det_lite
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input: float32[1, 480, 640, 1]Completion Time
5/2/2026, 8:23:51 AM
Versions
- LiteRT: 1.4.3
- QAIRT: v2.45.0.260326154327
- QNN TfLite Delegate: v2.45.0.260326154327
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.04.25.0
Estimated Inference Time
2.53 ms
Estimated Peak Memory Usage
0 ‑ 76 MB
Compute Units
NPU
86
| Stage | Time | Memory |
|---|---|---|
First App Load | 589 ms | 45‑46 MB |
Subsequent App Load | 207 ms | 3‑79 MB |
Inference | 2.53 ms | 0‑76 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