Profile Job Results
Jobs
jp4wwk11g
Results Ready
Name
trocr_float_TrOCREncoder
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
pixel_values: float32[1, 384, 384, 3]Completion Time
1/31/2026, 7:30:34 PM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.42.0.251225135753_193295
- QNN TfLite Delegate: v2.42.0.251225135753_193295
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.01.22.0
Estimated Inference Time
12.2 ms
Estimated Peak Memory Usage
0 ‑ 2 MB
Compute Units
NPU
603
| Stage | Time | Memory |
|---|---|---|
First App Load | 2.59 s | 347‑348 MB |
Subsequent App Load | 244 ms | 43‑84 MB |
Inference | 12.2 ms | 0‑2 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