Profile Job Results
Jobs
jp027je05
Results Ready
Name
convnext_tiny_w8a16
Target Device
- QCS6490 (Proxy)
- Android 12
- Qualcomm® QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_tensor: uint16[1, 224, 224, 3]Completion Time
10/5/2025, 12:41:51 PM
Versions
- QAIRT: v2.38.0.250901140452_125126
- QNN Backend API: 5.38.0
- QNN Core API: 2.28.1
- Android: 12 (SP1A.210812.016)
- AI Hub: aihub-2025.09.26.0
Estimated Inference Time
12.6 ms
Estimated Peak Memory Usage
0 ‑ 86 MB
Compute Units
NPU
223
| Stage | Time | Memory |
|---|---|---|
First App Load | 5.50 s | 388‑399 MB |
Subsequent App Load | 5.63 s | 377‑558 MB |
Inference | 12.6 ms | 0‑86 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