Profile Job Results
Jobs
jp0v2yn2g
Results Ready
Name
resnet34_ssd1200
Target Device
- Samsung Galaxy S26
- Android 16
- Snapdragon® 8 Elite Gen 5 for Galaxy | SM8850-AD
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: float32[1, 3, 1200, 1200]Completion Time
7/6/2026, 11:25:05 PM
Versions
- ONNX Runtime: 1.26.0
- QAIRT: v2.45.0.260326154327
- Android: 16 (BP4A.251205.006)
- AI Hub: aihub-2026.07.02.0
Estimated Inference Time
39.0 ms
Estimated Peak Memory Usage
1 ‑ 498 MB
Compute Units
NPU
944
| Stage | Time | Memory |
|---|---|---|
First App Load | 2.32 min | 776‑785 MB |
Subsequent App Load | 260 ms | 47‑546 MB |
Inference | 39.0 ms | 1‑498 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