Profile Job Results
Jobs
jpv1e47kp
Results Ready
Name
bevfusion_det_encoder_1
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
imgs: float32[1, 18, 256, 704]Completion Time
4/5/2026, 5:32:50 AM
Versions
- QAIRT: v2.43.0.260127150333_193827
- QNN Backend API: 5.43.0
- QNN Core API: 2.32.0
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.03.29.0
Estimated Inference Time
718 ms
Estimated Peak Memory Usage
13 ‑ 14 MB
Compute Units
NPU
636
| Stage | Time | Memory |
|---|---|---|
First App Load | 981 ms | 1‑3 MB |
Subsequent App Load | 877 ms | 1‑3 MB |
Inference | 718 ms | 13‑14 MB |
| QNN | Value |
|---|---|
| context_options.htp_options.performance_mode | BURST |
| default_graph_options.htp_options.optimizations[0].type | FINALIZE_OPTIMIZATION_FLAG |
| default_graph_options.htp_options.optimizations[0].value | 3.0 |
| default_graph_options.htp_options.precision | FLOAT16 |
| default_graph_options.htp_options.vtcm_size | 0 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device