Profile Job Results
Jobs
jg9jlk8v5
Results Ready
Name
resnet_3d
Target Device
- SA8650 (Proxy)
- Android 13
- Qualcomm® SA8650P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
video: float32[1, 16, 112, 112, 3]Completion Time
4/8/2025, 1:53:39 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
22.3 s
Estimated Peak Memory Usage
3,128 ‑ 866,291 GB
Compute Units
NPU
53
CPU
4
| Stage | Time | Memory |
|---|---|---|
First App Load | 120 min | 833,360‑834,509 GB |
Subsequent App Load | 124 min | 838,800‑841,312 GB |
Inference | 22.3 s | 3,128‑866,291 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 |
| XNNPACK Delegate | Value |
|---|
Sign up to run this model on a hosted Qualcomm® device!
Run on device