Profile Job Results
Jobs
jgkv434yp
Results Ready
Name
midas_quantized
Target Device
- QCS6490 (Proxy)
- Android 12
- Qualcomm® QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 256, 256, 3]Completion Time
3/11/2025, 8:49:56 PM
Versions
- QAIRT: v2.32.0.250228225014_116386
- QNN Backend API: 5.32.0
- QNN Core API: 2.24.0
- Android: 12 (SP1A.210812.016)
- AI Hub: aihub-2025.03.06.0
Estimated Inference Time
5.60 ms
Estimated Peak Memory Usage
0 ‑ 14 MB
Compute Units
NPU
198
| Stage | Time | Memory |
|---|---|---|
First App Load | 183 ms | 0‑7 MB |
Subsequent App Load | 158 ms | 0‑15 MB |
Inference | 5.60 ms | 0‑14 MB |
| QNN | Value |
|---|---|
| context_options.htp_options.performance_mode | BURST |
| default_graph_options.htp_options.precision | FLOAT16 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device