Profile Job Results
Jobs
jgz779dkp
Results Ready
Name
bisenet_w8a8
Target Device
- SA8295P ADP
- Android 14
- Qualcomm® SA8295P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 720, 960, 3]Completion Time
2/1/2026, 10:44:52 AM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.42.0.251225135753_193295
- QNN TfLite Delegate: v2.42.0.251225135753_193295
- Android: 14 (UQ1A.240205.002)
- Build ID: SA8295P.HQX.4.5.6.0-00006-STD.PROD-1
- AI Hub: aihub-2026.01.22.0
Estimated Inference Time
15.2 ms
Estimated Peak Memory Usage
8 ‑ 194 MB
Compute Units
NPU
69
| Stage | Time | Memory |
|---|---|---|
First App Load | 5.72 s | 230‑236 MB |
Subsequent App Load | 180 ms | 13‑199 MB |
Inference | 15.2 ms | 8‑194 MB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.precision | kHtpFp16 |
| htp_options.optimization_strategy | kHtpOptimizeForInferenceO3 |
| htp_options.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device