Profile Job Results
Jobs
jp4dx1xlp
Results Ready
Name
deeplabv3_resnet50
Target Device
- Snapdragon 8 Elite QRD
- Android 15
- Snapdragon® 8 Elite | SM8750
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 3, 520, 520]Completion Time
7/26/2025, 11:35:16 PM
Versions
- ONNX Runtime: 1.22.0
- QAIRT: v2.34.2.250528164111_119506
- Android: 15 (AQ3A.241126.002)
- Build ID: Pakala.LA.1.0.r1-01152-STD.PROD-1
- AI Hub: aihub-2025.07.12.0
Estimated Inference Time
4.65 min
Estimated Peak Memory Usage
37 ‑ 367 MB
Compute Units
NPU
98
CPU
2
| Stage | Time | Memory |
|---|---|---|
First App Load | 18.9 s | 671‑677 MB |
Subsequent App Load | 20.2 s | 506‑965 MB |
Inference | 4.65 min | 37‑367 MB |
| ONNX Runtime | Value |
|---|---|
| execution_mode | SEQUENTIAL |
| intra_op_num_threads | 0 |
| inter_op_num_threads | 0 |
| enable_memory_pattern | false |
| enable_cpu_memory_arena | false |
| graph_optimization_level | ENABLE_ALL |
| QNN Execution Provider | Value |
|---|---|
| htp_performance_mode | "burst" |
| htp_graph_finalization_optimization_mode | "3" |
| enable_htp_fp16_precision | "1" |
| capture_network_visualizations | false |
Sign up to run this model on a hosted Qualcomm® device!
Run on device