Profile Job Results
Jobs
jpr8x0105
Results Ready
Name
depth_anything_v2
Target Device
- SA8650 (Proxy)
- Android 13
- Qualcomm® SA8650P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 518, 518, 3]Completion Time
5/21/2025, 7:14:50 AM
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
138 ms
Estimated Peak Memory Usage
1 ‑ 101 MB
Compute Units
NPU
646
| Stage | Time | Memory |
|---|---|---|
First App Load | 21.3 s | 1 GB |
Subsequent App Load | 21.2 s | 1 GB |
Inference | 138 ms | 1‑101 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 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device