Profile Job Results
Jobs
jgl32w1eg
Results Ready
Name
resnet_mixed_w8a16
Target Device
- QCS6490 (Proxy)
- Android 12
- Qualcomm® QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
video: uint16[1, 16, 112, 112, 3]Completion Time
10/26/2025, 3:14:10 AM
Options
--qairt_version latestVersions
- QAIRT: v2.39.0.250925215840_163802
- QNN Backend API: 5.39.0
- QNN Core API: 2.29.0
- Android: 12 (SP1A.210812.016)
- AI Hub: aihub-2025.10.21.0
Estimated Inference Time
55.2 ms
Estimated Peak Memory Usage
1 ‑ 66 MB
Compute Units
NPU
53
| Stage | Time | Memory |
|---|---|---|
First App Load | 6.39 s | 321‑332 MB |
Subsequent App Load | 6.66 s | 267‑417 MB |
Inference | 55.2 ms | 1‑66 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