Profile Job Results
Jobs
jglwm38lp
Results Ready
Name
deeplabv3_plus_mobilenet
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® Dragonwing™ QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: uint8[1, 520, 520, 3]Completion Time
10/3/2026, 4:20:21 PM
Versions
- QAIRT: v2.50.0.260828221209
- QNN Backend API: 5.50.0
- QNN Core API: 2.39.0
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2026.09.25.0
Estimated Inference Time
4.11 ms
Estimated Peak Memory Usage
1 ‑ 39 MB
Compute Units
NPU
128
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.56 s | 133‑134 MB |
Subsequent App Load | 207 ms | 1‑40 MB |
Inference | 4.11 ms | 1‑39 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