Profile Job Results
Jobs
j5611xdvp
Results Ready
Name
detr_resnet101_float
Target Device
- QCS8450 (Proxy)
- Android 13
- Qualcomm® QCS8450
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 640, 640, 3]Completion Time
2/1/2026, 8:48:36 AM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.42.0.251225135753_193295
- QNN TfLite Delegate: v2.42.0.251225135753_193295
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2026.01.22.0
Estimated Inference Time
54.9 ms
Estimated Peak Memory Usage
0 ‑ 420 MB
Compute Units
NPU
869
| Stage | Time | Memory |
|---|---|---|
First App Load | 10.5 s | 811‑820 MB |
Subsequent App Load | 320 ms | 118‑530 MB |
Inference | 54.9 ms | 0‑420 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