Profile Job Results
Jobs
jgdvwmllg
Results Ready
Name
trocr_TrOCREncoder
Target Device
- Samsung Galaxy S24
- Android 14
- Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
pixel_values: float32[1, 384, 384, 3]Completion Time
3/7/2026, 9:33:32 AM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.43.0.260127150333_193827
- QNN TfLite Delegate: v2.43.0.260127150333_193827
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.02.26.0
Estimated Inference Time
8.51 ms
Estimated Peak Memory Usage
61 ‑ 288 MB
Compute Units
NPU
603
| Stage | Time | Memory |
|---|---|---|
First App Load | 3.09 s | 258‑265 MB |
Subsequent App Load | 205 ms | 84‑314 MB |
Inference | 8.51 ms | 61‑288 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.optimization_strategy | kHtpOptimizeForInferenceO3 |
| htp_options.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device