Profile Job Results
Jobs
jgl32l62g
Results Ready
Name
trocr_float_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
10/25/2025, 3:34:44 PM
Options
--qairt_version latestVersions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.39.0.250925215840_163802
- QNN TfLite Delegate: v2.39.0.250925215840_163802
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.10.21.0
Estimated Inference Time
13.3 ms
Estimated Peak Memory Usage
7 ‑ 29 MB
Compute Units
NPU
603
| Stage | Time | Memory |
|---|---|---|
First App Load | 2.64 s | 372‑373 MB |
Subsequent App Load | 2.55 s | 398‑400 MB |
Inference | 13.3 ms | 7‑29 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