Profile Job Results
Jobs
jp4n1v7vg
Results Ready
Name
ffnet_78s_quantized
Target Device
- Samsung Galaxy S24 (Family)
- Android 14
- Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 1024, 2048, 3]Completion Time
3/11/2025, 9:02:33 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-2025.03.06.0
Estimated Inference Time
7.67 ms
Estimated Peak Memory Usage
1 ‑ 75 MB
Compute Units
NPU
153
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.42 s | 348‑355 MB |
Subsequent App Load | 1.46 s | 413‑542 MB |
Inference | 7.67 ms | 1‑75 MB |
| 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