Profile Job Results
Jobs
jpevmw385
Results Ready
Name
face_det_lite_w8a16
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
input: uint16[1, 480, 640, 1]Completion Time
1/11/2026, 2:51:45 AM
Options
--qairt_version latestVersions
- QAIRT: v2.41.0.251128145156_191518
- QNN Backend API: 5.41.0
- QNN Core API: 2.31.0
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.01.05.0
Estimated Inference Time
1.70 ms
Estimated Peak Memory Usage
1 ‑ 3 MB
Compute Units
NPU
127
| Stage | Time | Memory |
|---|---|---|
First App Load | 575 ms | 114‑116 MB |
Subsequent App Load | 211 ms | 1‑136 MB |
Inference | 1.70 ms | 1‑3 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