Profile Job Results
Jobs
jpry31k0g
Results Ready
Name
ddrnet23_slim_float
Target Device
- SA8650 (Proxy)
- Android 13
- Qualcomm® SA8650P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 1024, 2048, 3]Completion Time
1/11/2026, 7:29:57 AM
Options
--qairt_version latestVersions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.41.0.251128145156_191518
- QNN TfLite Delegate: v2.41.0.251128145156_191518
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2026.01.05.0
Estimated Inference Time
30.7 ms
Estimated Peak Memory Usage
2 ‑ 6 MB
Compute Units
NPU
133
| Stage | Time | Memory |
|---|---|---|
First App Load | 3.89 s | 258‑259 MB |
Subsequent App Load | 209 ms | 13‑21 MB |
Inference | 30.7 ms | 2‑6 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.optimization_strategy | kHtpOptimizeForInferenceO3 |
| htp_options.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device