Profile Job Results
Jobs
jp1wj3e8g
Results Ready
Name
lama_dilated
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 512, 512, 3]mask: float32[1, 512, 512, 1]Completion Time
8/23/2025, 11:51:28 PM
Options
--qairt_version latestVersions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.37.0.250724175447_124859
- QNN TfLite Delegate: v2.37.0.250724175447_124859
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.08.21.0
Estimated Inference Time
87.0 ms
Estimated Peak Memory Usage
3 ‑ 314 MB
Compute Units
NPU
340
| Stage | Time | Memory |
|---|---|---|
First App Load | 8.76 s | 711‑713 MB |
Subsequent App Load | 10.1 s | 751‑754 MB |
Inference | 87.0 ms | 3‑314 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