Profile Job Results
Jobs
jgl0m702g
Results Ready
Name
unet_segmentation
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 640, 1280, 3]Completion Time
3/14/2026, 7:28:42 PM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.43.0.260127150333_193827
- QNN TfLite Delegate: v2.43.0.260127150333_193827
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2026.03.09.0
Estimated Inference Time
140 ms
Estimated Peak Memory Usage
0 ‑ 305 MB
Compute Units
NPU
31
| Stage | Time | Memory |
|---|---|---|
First App Load | 25.7 s | 550‑551 MB |
Subsequent App Load | 303 ms | 0‑502 MB |
Inference | 140 ms | 0‑305 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.optimization_strategy | kHtpOptimizeForInferenceO3 |
| htp_options.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device