Profile Job Results
Jobs
jp03dn12p
Results Ready
Name
efficientvit_l2_cls
Target Device
- SA7255P ADP
- Android 14
- Qualcomm® SA7255P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_tensor: float32[1, 224, 224, 3]Completion Time
5/6/2025, 5:47:56 PM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.32.6.250402152434_116405-auto
- QNN TfLite Delegate: v2.32.6.250402152434_116405-auto
- Android: 14 (UQ1A.240205.002)
- Build ID: Snapdragon_Auto.HQX.4.5.6.0.r2-00012-STD.PROD-5
- AI Hub: aihub-2025.05.02.0
Estimated Inference Time
23.8 ms
Estimated Peak Memory Usage
0 ‑ 192 MB
Compute Units
NPU
349
| Stage | Time | Memory |
|---|---|---|
First App Load | 16.7 s | 1 GB |
Subsequent App Load | 16.9 s | 1 GB |
Inference | 23.8 ms | 0‑192 MB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.precision | kHtpFp16 |
| htp_options.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device