Profile Job Results
Jobs
jgn3md4r5
Results Ready
Name
litehrnet_float
Target Device
- SA8650 (Proxy)
- Android 13
- Qualcomm® SA8650P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 3, 256, 192]Completion Time
10/25/2025, 7:42:23 PM
Options
--qairt_version latestVersions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.39.0.250925215840_163802
- QNN TfLite Delegate: v2.39.0.250925215840_163802
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.10.21.0
Estimated Inference Time
4.47 ms
Estimated Peak Memory Usage
0 ‑ 19 MB
Compute Units
NPU
1110
CPU
2
| Stage | Time | Memory |
|---|---|---|
First App Load | 2.30 s | 134‑135 MB |
Subsequent App Load | 2.33 s | 162‑166 MB |
Inference | 4.47 ms | 0‑19 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