Profile Job Results
Jobs
jp16ozx25
Results Ready
Name
bevdet_encoder
Target Device
- Samsung Galaxy S24
- Android 14
- Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: float32[1, 18, 256, 704]Completion Time
8/8/2026, 4:48:38 PM
Versions
- Lite RT: 1.4.5
- QAIRT: v2.45.0.260326154327
- QNN TfLite Delegate: v2.45.0.260326154327
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.07.31.1
Estimated Inference Time
36.0 ms
Estimated Peak Memory Usage
24 ‑ 483 MB
Compute Units
NPU
93
CPU
1
| Stage | Time | Memory |
|---|---|---|
First App Load | 12.9 s | 464‑471 MB |
Subsequent App Load | 282 ms | 123‑582 MB |
Inference | 36.0 ms | 24‑483 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