Profile Job Results
Jobs
jpr60vd9p
Results Ready
Name
inception_v3
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_tensor: float32[1, 224, 224, 3]Completion Time
3/11/2025, 4:37:46 PM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.32.0.250228225014_116386
- QNN TfLite Delegate: v2.32.0.250228225014_116386
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2025.03.06.0
Estimated Inference Time
1.33 ms
Estimated Peak Memory Usage
0 ‑ 334 MB
Compute Units
NPU
129
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.94 s | 315‑321 MB |
Subsequent App Load | 1.84 s | 356‑360 MB |
Inference | 1.33 ms | 0‑334 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