Profile Job Results
Jobs
jgk4jwoop
Results Ready
Name
efficientvit_l2_cls
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® Dragonwing™ QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image_tensor: uint16[1, 3, 384, 384]Completion Time
9/5/2026, 3:24:49 PM
Versions
- QAIRT: v2.45.0.260326154327
- QNN Backend API: 5.45.0
- QNN Core API: 2.34.0
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2026.08.28.1
Estimated Inference Time
14.5 ms
Estimated Peak Memory Usage
1 ‑ 279 MB
Compute Units
NPU
348
| Stage | Time | Memory |
|---|---|---|
First App Load | 6.77 s | 339‑340 MB |
Subsequent App Load | 254 ms | 1‑280 MB |
Inference | 14.5 ms | 1‑279 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