Profile Job Results
Jobs
jgnnen2rg
Results Ready
Name
owl_vit
Target Device
- SA8775P ADP
- Android 14
- Qualcomm® SA8775P
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
pixel_values: float32[1, 3, 768, 768]input_ids: int32[1, 16]attention_mask: int32[1, 16]Completion Time
8/22/2026, 9:50:17 PM
Versions
- Lite RT: 1.4.5
- QAIRT: v2.45.0.260326154327
- QNN TfLite Delegate: v2.45.0.260326154327
- Android: 14 (UAG2.240908.001)
- Build ID: Snapdragon_Auto.HQX.4.5.6.0.r2-00016-STD.PROD-3
- AI Hub: aihub-2026.08.14.0
Estimated Inference Time
39.3 ms
Estimated Peak Memory Usage
0 ‑ 471 MB
Compute Units
NPU
1202
CPU
1
| Stage | Time | Memory |
|---|---|---|
First App Load | 56.1 s | 809‑814 MB |
Subsequent App Load | 1.28 s | 279‑751 MB |
Inference | 39.3 ms | 0‑471 MB |
| Lite RT | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.precision | kHtpFp16 |
| htp_options.optimization_strategy | kHtpOptimizeForInferenceO3 |
| htp_options.useConvHmx | true |
| htp_options.device_id | 1 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device