Profile Job Results
Jobs
j5m6r9z9g
Results Ready
Name
trocr_TrOCREncoder
Target Device
- SA8255 (Proxy)
- Android 13
- Qualcomm® SA8255P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
pixel_values: float32[1, 384, 384, 3]Completion Time
9/27/2025, 6:01:54 PM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.38.0.250901140452_125126
- QNN TfLite Delegate: v2.38.0.250901140452_125126
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.09.23.1
Estimated Inference Time
17.9 ms
Estimated Peak Memory Usage
7 ‑ 24 MB
Compute Units
NPU
603
| Stage | Time | Memory |
|---|---|---|
First App Load | 2.70 s | 465‑466 MB |
Subsequent App Load | 2.77 s | 476‑478 MB |
Inference | 17.9 ms | 7‑24 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