Profile Job Results
Jobs
jgonywx4p
Results Ready
Name
rf_detr
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 560, 560, 3]Completion Time
9/28/2025, 1:45:01 AM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.38.0.250901140452_125126
- QNN TfLite Delegate: v2.38.0.250901140452_125126
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2025.09.23.1
Estimated Inference Time
105 ms
Estimated Peak Memory Usage
6 ‑ 34 MB
Compute Units
NPU
1206
CPU
26
| Stage | Time | Memory |
|---|---|---|
First App Load | 33.7 s | 706‑708 MB |
Subsequent App Load | 33.7 s | 745‑750 MB |
Inference | 105 ms | 6‑34 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 |
| XNNPACK Delegate | Value |
|---|
Sign up to run this model on a hosted Qualcomm® device!
Run on device