Profile Job Results
Jobs
j5qr7ywmp
Results Ready
Name
deeplabv3_plus_mobilenet
Target Device
- QCS6490 (Proxy)
- Android 12
- Qualcomm® QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint16[1, 520, 520, 3]Completion Time
7/26/2025, 11:33:49 PM
Versions
- QAIRT: v2.34.2.250528164111_119506
- QNN Backend API: 5.34.0
- QNN Core API: 2.25.0
- Android: 12 (SP1A.210812.016)
- AI Hub: aihub-2025.07.12.0
Estimated Inference Time
44.1 ms
Estimated Peak Memory Usage
2 ‑ 91 MB
Compute Units
NPU
85
| Stage | Time | Memory |
|---|---|---|
First App Load | 4.13 s | 185‑196 MB |
Subsequent App Load | 4.48 s | 167‑284 MB |
Inference | 44.1 ms | 2‑91 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