Profile Job Results
Jobs
jpeozvj1g
Results Ready
Name
video_mae_quantized
Target Device
- Samsung Galaxy S24 (Family)
- Android 14
- Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
video: uint8[1, 16, 224, 224, 3]Completion Time
3/11/2025, 9:52:34 PM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.32.0.250228225014_116386
- QNN TfLite Delegate: v2.32.0.250228225014_116386
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2025.03.06.0
Estimated Inference Time
407 ms
Estimated Peak Memory Usage
2 ‑ 354 MB
Compute Units
NPU
611
CPU
1
| Stage | Time | Memory |
|---|---|---|
First App Load | 15.4 s | 1 GB |
Subsequent App Load | 15.5 s | 1‑2 GB |
Inference | 407 ms | 2‑354 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