Profile Job Results
Jobs
jg9yv1eq5
Results Ready
Name
depth_anything_v2
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 3, 518, 518]Completion Time
9/28/2025, 2:30:31 AM
Options
--qairt_version 2.37Versions
- ONNX Runtime: 1.22.2
- QAIRT: v2.37.1.250807093845_124904
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2025.09.23.1
Estimated Inference Time
77.9 ms
Estimated Peak Memory Usage
4 ‑ 34 MB
Compute Units
NPU
472
| Stage | Time | Memory |
|---|---|---|
First App Load | 34.4 s | 912‑913 MB |
Subsequent App Load | 38.9 s | 948‑952 MB |
Inference | 77.9 ms | 4‑34 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