Profile Job Results
Jobs
jpr8x4ok5
Results Ready
Name
resnet_mixed
Target Device
- XR2 Gen 2 (Proxy)
- Android 13
- Qualcomm® QCS8450
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
video: float32[1, 16, 112, 112, 3]Completion Time
5/20/2025, 3:27:37 PM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.32.6.250402152434_116405
- QNN TfLite Delegate: v2.32.6.250402152434_116405
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.05.14.0
Estimated Inference Time
150 ms
Estimated Peak Memory Usage
31 ‑ 67 MB
Compute Units
NPU
53
CPU
4
| Stage | Time | Memory |
|---|---|---|
First App Load | 9.15 s | 379‑389 MB |
Subsequent App Load | 7.66 s | 279‑387 MB |
Inference | 150 ms | 31‑67 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 |
| XNNPACK Delegate | Value |
|---|
Sign up to run this model on a hosted Qualcomm® device!
Run on device