Profile Job Results
Jobs
jgl6v1jjg
Results Ready
Name
mobilenet_v3_small
Target Device
- SA8255 (Proxy)
- Android 13
- Qualcomm® SA8255P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_tensor: float32[1, 224, 224, 3]Completion Time
4/8/2025, 3:11:37 PM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.32.0.250228225014_116386
- QNN TfLite Delegate: v2.32.0.250228225014_116386
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.03.24.0
Estimated Inference Time
763 ms
Estimated Peak Memory Usage
20 ‑ 46,240 GB
Compute Units
NPU
115
| Stage | Time | Memory |
|---|---|---|
First App Load | 8.69 min | 40,612‑41,799 GB |
Subsequent App Load | 7.83 min | 71,196‑73,521 GB |
Inference | 763 ms | 20‑46,240 GB |
| 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