Profile Job Results
Jobs
jg9d0n9v5
Results Ready
Name
mediapipe_hand_gesture_hand_landmark_detector
Target Device
- Dragonwing RB3 Gen 2 Vision Kit
- Qualcomm Linux 1.6
- Qualcomm® Dragonwing™ RB3 Gen 2 | QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: uint8[1, 224, 224, 3]Completion Time
7/26/2026, 1:50:16 AM
Versions
- Lite RT: 1.4.4
- QAIRT: v2.45.0.260326154327
- QNN TfLite Delegate: v2.45.0.260326154327
- Qualcomm Linux: 1.6-ver.1.2
- AI Hub: aihub-2026.07.17.0
Estimated Inference Time
1.01 ms
Estimated Peak Memory Usage
0 ‑ 10 MB
Compute Units
NPU
68
| Stage | Time | Memory |
|---|---|---|
First App Load | 644 ms | 110‑111 MB |
Subsequent App Load | 186 ms | 10‑11 MB |
Inference | 1.01 ms | 0‑10 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