Profile Job Results
Jobs
jgl4xvee5
Results Ready
Name
mediapipe_face_quantized_MediaPipeFaceLandmarkDetector
Target Device
- SA8255 (Proxy)
- Android 13
- Qualcomm® SA8255P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 192, 192, 3]Completion Time
3/11/2025, 4:20:27 PM
Versions
- QAIRT: v2.32.0.250228225014_116386
- QNN Backend API: 5.32.0
- QNN Core API: 2.24.0
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.03.06.0
Estimated Inference Time
153 μs
Estimated Peak Memory Usage
0 ‑ 2 MB
Compute Units
NPU
112
| Stage | Time | Memory |
|---|---|---|
First App Load | 168 ms | 1‑2 MB |
Subsequent App Load | 149 ms | 1‑2 MB |
Inference | 153 μs | 0‑2 MB |
| QNN | Value |
|---|---|
| context_options.htp_options.performance_mode | BURST |
| default_graph_options.htp_options.precision | FLOAT16 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device