Profile Job Results
Jobs
jpee6y07p
Results Ready
Name
efficientnet_b4
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
5/21/2025, 6:14:07 AM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.32.6.250402152434_116405
- QNN TfLite Delegate: v2.32.6.250402152434_116405
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2025.05.14.0
Estimated Inference Time
3.33 ms
Estimated Peak Memory Usage
0 ‑ 386 MB
Compute Units
NPU
482
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.99 s | 400‑401 MB |
Subsequent App Load | 1.98 s | 433‑435 MB |
Inference | 3.33 ms | 0‑386 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