Profile Job Results
Jobs
jp3vxrr3g
Results Ready
Name
mediapipe_face_FaceLandmarkDetector
Target Device
- Snapdragon 8 Elite QRD
- Android 15
- Snapdragon® 8 Elite | SM8750
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 192, 192, 3]Completion Time
5/6/2025, 2:45:15 PM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.32.6.250402152434_116405
- QNN TfLite Delegate: v2.32.6.250402152434_116405
- Android: 15 (AQ3A.241126.002)
- Build ID: Pakala.LA.1.0.r1-01152-STD.PROD-1
- AI Hub: aihub-2025.05.02.0
Estimated Inference Time
123 μs
Estimated Peak Memory Usage
0 ‑ 18 MB
Compute Units
NPU
108
| Stage | Time | Memory |
|---|---|---|
First App Load | 225 ms | 23‑30 MB |
Subsequent App Load | 218 ms | 0‑23 MB |
Inference | 123 μs | 0‑18 MB |
| TensorFlow Lite | 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.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device