Profile Job Results
Jobs
jp4w16xlg
Results Ready
Name
eyegaze
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 96, 160]Completion Time
2/22/2026, 12:16:33 PM
Options
--compute_unit cpuVersions
- QAIRT: v2.43.0.260127150333_193827
- QNN Backend API: 1.1.0
- QNN Core API: 2.32.0
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2026.02.14.0
Estimated Inference Time
45.0 ms
Estimated Peak Memory Usage
35 ‑ 41 MB
Compute Units
CPU
481
| Stage | Time | Memory |
|---|---|---|
First App Load | 72.5 ms | 26‑27 MB |
Subsequent App Load | 54.5 ms | 0‑57 MB |
Inference | 45.0 ms | 35‑41 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