Profile Job Results
Jobs
jp1y4jdkp
Results Ready
Name
ffnet_54s
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 1024, 2048, 3]Completion Time
4/8/2025, 4:57:34 PM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.32.0.250228225014_116386
- QNN TfLite Delegate: v2.32.0.250228225014_116386
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2025.03.24.0
Estimated Inference Time
9.65 s
Estimated Peak Memory Usage
652 ‑ 15,942 GB
Compute Units
NPU
117
| Stage | Time | Memory |
|---|---|---|
First App Load | 20.7 min | 133,076‑134,230 GB |
Subsequent App Load | 21.5 min | 162,388‑164,570 GB |
Inference | 9.65 s | 652‑15,942 GB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.performance_mode | kHtpBurst |
| htp_options.precision | kHtpFp16 |
| htp_options.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device