Profile Job Results
Jobs
jp38yvyl5
Results Ready
Name
mediapipe_face_face_landmark_detector
Target Device
- Dragonwing IQ-9075 EVK
- Qualcomm Linux 1.7
- Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: float32[1, 192, 192, 3]Completion Time
6/14/2026, 3:09:52 AM
Versions
- LiteRT: 1.4.4
- QAIRT: v2.45.0.260326154327
- QNN TfLite Delegate: v2.45.0.260326154327
- Qualcomm Linux: 1.7-ver.1.1
- AI Hub: aihub-2026.06.08.2
Estimated Inference Time
309 μs
Estimated Peak Memory Usage
0 ‑ 4 MB
Compute Units
NPU
99
| Stage | Time | Memory |
|---|---|---|
First App Load | 504 ms | 100 MB |
Subsequent App Load | 179 ms | 7‑8 MB |
Inference | 309 μs | 0‑4 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 | kHtpOptimizeForInference |
| htp_options.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device