Profile Job Results
Jobs
j57or1n9g
Results Ready
Name
mediapipe_face_face_landmark_detector
Target Device
- Snapdragon 7 Gen 4 QRD
- Android 15
- Snapdragon® 7 Gen 4 | SM7750
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: uint8[1, 192, 192, 3]Completion Time
10/4/2026, 7:01:37 AM
Versions
- Lite RT: 1.4.2
- QAIRT: v2.50.0.260828221209
- QNN TfLite Delegate: v2.50.0.260828221209
- Android: 15 (AQ3A.250411.001)
- Build ID: Eliza.LA.1.0.r1-00181-STD.PROD-1
- AI Hub: aihub-2026.09.25.0
Estimated Inference Time
144 μs
Estimated Peak Memory Usage
0 ‑ 26 MB
Compute Units
NPU
106
| Stage | Time | Memory |
|---|---|---|
First App Load | 530 ms | 42‑49 MB |
Subsequent App Load | 129 ms | 0‑29 MB |
Inference | 144 μs | 0‑26 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