Profile Job Results
Jobs
jp04jl79g
Results Ready
Name
ffnet_40s_quantized
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
3/11/2025, 9:07:18 PM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.32.0.250228225014_116386
- QNN TfLite Delegate: v2.32.0.250228225014_116386
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.03.06.0
Estimated Inference Time
8.82 ms
Estimated Peak Memory Usage
1 ‑ 10 MB
Compute Units
NPU
96
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.27 s | 133‑134 MB |
Subsequent App Load | 1.50 s | 126‑128 MB |
Inference | 8.82 ms | 1‑10 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