Profile Job Results
Jobs
jp1ve4elp
Results Ready
Name
mediapipe_hand_gesture_canned_gesture_classifier
Target Device
- Samsung Galaxy S22 5G
- Android 12
- Snapdragon® 8 Gen 1 | SM8450
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
hand: uint8[1, 64]mirrored_hand: uint8[1, 64]Completion Time
7/7/2026, 1:27:36 AM
Versions
- LiteRT: 1.4.4
- QAIRT: v2.45.0.260326154327
- QNN TfLite Delegate: v2.45.0.260326154327
- Android: 12 (SP1A.210812.016)
- AI Hub: aihub-2026.07.02.0
Estimated Inference Time
97.0 μs
Estimated Peak Memory Usage
0 ‑ 31 MB
Compute Units
NPU
99
| Stage | Time | Memory |
|---|---|---|
First App Load | 298 ms | 27‑37 MB |
Subsequent App Load | 167 ms | 2‑34 MB |
Inference | 97.0 μs | 0‑31 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