Profile Job Results
Jobs
j5w3on73p
Results Ready
Name
deepbox_VGG3DDetection
Target Device
- Samsung Galaxy S24
- Android 14
- Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 224, 224, 3]Completion Time
9/27/2025, 11:55:41 PM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.38.0.250901140452_125126
- QNN TfLite Delegate: v2.38.0.250901140452_125126
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2025.09.23.1
Estimated Inference Time
3.97 ms
Estimated Peak Memory Usage
0 ‑ 129 MB
Compute Units
NPU
43
| Stage | Time | Memory |
|---|---|---|
First App Load | 2.87 s | 781‑789 MB |
Subsequent App Load | 2.93 s | 1 GB |
Inference | 3.97 ms | 0‑129 MB |
| TensorFlow Lite | 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.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device