Profile Job Results
Jobs
jg9w7djlp
Results Ready
Name
inception_v3_float
Target Device
- SA8650 (Proxy)
- Android 13
- Qualcomm® SA8650P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_tensor: float32[1, 224, 224, 3]Completion Time
12/14/2025, 1:11:03 AM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.40.0.251030114326_189385
- QNN TfLite Delegate: v2.40.0.251030114326_189385
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.12.07.0
Estimated Inference Time
1.31 ms
Estimated Peak Memory Usage
0 ‑ 367 MB
Compute Units
NPU
129
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.91 s | 392‑394 MB |
Subsequent App Load | 1.89 s | 421‑424 MB |
Inference | 1.31 ms | 0‑367 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