Profile Job Results
Jobs
j5m6m647g
Results Ready
Name
video_mae
Target Device
- XR2 Gen 2 (Proxy)
- Android 13
- Qualcomm® QCS8450
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
video: float32[1, 16, 224, 224, 3]Completion Time
8/23/2025, 8:03:37 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
220 ms
Estimated Peak Memory Usage
3 ‑ 486 MB
Compute Units
NPU
558
| Stage | Time | Memory |
|---|---|---|
First App Load | 30.9 s | 2 GB |
Subsequent App Load | 34.4 s | 2‑3 GB |
Inference | 220 ms | 3‑486 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