Profile Job Results
Jobs
jegn1qdvp
Results Ready
Name
ffnet_78s_quantized
Target Device
- Samsung Galaxy S24+
- 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
8/11/2024, 8:16:59 AM
Versions
- TensorFlow Lite: 2.16.1
- QNN TfLite Delegate: v2.24.0.240626131148_96320
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2024.08.01.0
Estimated Inference Time
4.08 ms
Estimated Peak Memory Usage
1 - 81 MB
Compute Units
NPU
156
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.15 s | 258-266 MB |
Subsequent App Load | 186 ms | 27-109 MB |
Inference | 4.08 ms | 1-81 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