Profile Job Results
Jobs
jgj7j818g
Results Ready
Name
mediapipe_face_face_landmark_detector
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® Dragonwing™ QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: uint8[1, 192, 192, 3]Completion Time
9/5/2026, 2:34:17 PM
Versions
- Lite RT: 1.4.5
- QAIRT: v2.45.0.260326154327
- QNN TfLite Delegate: v2.45.0.260326154327
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.08.28.1
Estimated Inference Time
151 μs
Estimated Peak Memory Usage
0 ‑ 2 MB
Compute Units
NPU
106
| Stage | Time | Memory |
|---|---|---|
First App Load | 479 ms | 32‑33 MB |
Subsequent App Load | 199 ms | 1‑22 MB |
Inference | 151 μs | 0‑2 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