Profile Job Results
Jobs
jgj2okex5
Results Ready
Name
mediapipe_pose_PoseLandmarkDetector
Target Device
- SA8650 (Proxy)
- Android 13
- Qualcomm® SA8650P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 256, 256, 3]Completion Time
8/9/2025, 8:30:02 PM
Versions
- QAIRT: v2.34.2.250528164111_119506
- QNN Backend API: 5.34.0
- QNN Core API: 2.25.0
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.07.25.0
Estimated Inference Time
791 μs
Estimated Peak Memory Usage
0 ‑ 47 MB
Compute Units
NPU
291
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.33 s | 109‑110 MB |
Subsequent App Load | 1.20 s | 135‑137 MB |
Inference | 791 μs | 0‑47 MB |
| QNN | Value |
|---|---|
| context_options.htp_options.performance_mode | BURST |
| default_graph_options.htp_options.optimizations[0].type | FINALIZE_OPTIMIZATION_FLAG |
| default_graph_options.htp_options.optimizations[0].value | 3.0 |
| default_graph_options.htp_options.precision | FLOAT16 |
| default_graph_options.htp_options.vtcm_size | 0 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device