Profile Job Results
Jobs
jp43nr615
Results Ready
Name
mediapipe_hand_gesture_canned_gesture_classifier
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® Dragonwing™ QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
hand: float32[1, 64]mirrored_hand: float32[1, 64]Completion Time
7/26/2026, 2:04:15 AM
Versions
- Lite RT: 1.4.4
- QAIRT: v2.45.0.260326154327
- QNN TfLite Delegate: v2.45.0.260326154327
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2026.07.17.0
Estimated Inference Time
77.0 μs
Estimated Peak Memory Usage
0 ‑ 4 MB
Compute Units
NPU
94
| Stage | Time | Memory |
|---|---|---|
First App Load | 338 ms | 25‑26 MB |
Subsequent App Load | 198 ms | 1‑18 MB |
Inference | 77.0 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 | kHtpOptimizeForInferenceO3 |
| htp_options.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device