Profile Job Results
Jobs
jw56o0mn5
Results Ready
Name
convnext_tiny_w8a16_quantized
Target Device
- XR2 Gen 2 (Proxy)
- Android 13
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_tensor: uint16[1, 224, 224, 3]Completion Time
8/11/2024, 9:22:51 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
4.42 ms
Estimated Peak Memory Usage
0 - 33 MB
Compute Units
NPU
215
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.55 s | 388-397 MB |
Subsequent App Load | 1.76 s | 200-351 MB |
Inference | 4.42 ms | 0-33 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