Profile Job Results
Jobs
jpr16eyvg
Results Ready
Name
detr_resnet50_dc5
Target Device
- Samsung Galaxy S24
- Android 14
- Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: float32[1, 3, 640, 640]Completion Time
5/3/2026, 1:29:13 AM
Options
--qairt_version 2.42Versions
- ONNX Runtime: 1.24.3
- QAIRT: v2.42.0.251225135753_193295
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.04.25.0
Estimated Inference Time
31.3 ms
Estimated Peak Memory Usage
0 ‑ 630 MB
Compute Units
NPU
688
| Stage | Time | Memory |
|---|---|---|
First App Load | 15.7 s | 791‑798 MB |
Subsequent App Load | 199 ms | 193‑825 MB |
Inference | 31.3 ms | 0‑630 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 |
| context_priority | "normal" |
| offload_graph_io_quantization | "1" |
Sign up to run this model on a hosted Qualcomm® device!
Run on device