Profile Job Results
Jobs
j1glwwnlp
Results Ready
Name
mobilenet_v3_large_quantized
Target Device
- XR2 Gen 2 (Proxy)
- Android 13
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_tensor: uint8[1, 224, 224, 3]Completion Time
8/11/2024, 7:43:34 AM
Versions
- QNN: v2.24.0.240626131148_96320
- QNN Backend API: 5.24.0
- QNN Core API: 2.17.0
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2024.08.01.0
Estimated Inference Time
0.78 ms
Estimated Peak Memory Usage
0 - 19 MB
Compute Units
NPU
126
| Stage | Time | Memory |
|---|---|---|
First App Load | 507 ms | 78-87 MB |
Subsequent App Load | 510 ms | 26-77 MB |
Inference | 0.78 ms | 0-19 MB |
| QNN | Value |
|---|---|
| context_options.htp_options.performance_mode | BURST |
| default_graph_options.htp_options.precision | FLOAT16 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device