Profile Job Results
Jobs
jg9we26vp
Results Ready
Name
unet_segmentation_w8a8
Target Device
- QCS8450 (Proxy)
- Android 13
- Qualcomm® QCS8450
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 640, 1280, 3]Completion Time
1/10/2026, 6:12:31 PM
Options
--qairt_version latestVersions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.41.0.251128145156_191518
- QNN TfLite Delegate: v2.41.0.251128145156_191518
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2026.01.05.0
Estimated Inference Time
58.3 ms
Estimated Peak Memory Usage
0 ‑ 296 MB
Compute Units
NPU
37
| Stage | Time | Memory |
|---|---|---|
First App Load | 2.69 s | 547‑555 MB |
Subsequent App Load | 266 ms | 34‑332 MB |
Inference | 58.3 ms | 0‑296 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