Profile Job Results
Jobs
jgnxjmwm5
Results Ready
Name
mediapipe_hand_gesture_canned_gesture_classifier
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
hand: uint8[1, 64]mirrored_hand: uint8[1, 64]Completion Time
6/14/2026, 3:47:49 AM
Versions
- LiteRT: 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-2026.06.08.2
Estimated Inference Time
221 μs
Estimated Peak Memory Usage
0 ‑ 2 MB
Compute Units
NPU
99
| Stage | Time | Memory |
|---|---|---|
First App Load | 408 ms | 97‑98 MB |
Subsequent App Load | 151 ms | 2‑3 MB |
Inference | 221 μs | 0‑2 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