Profile Job Results
Jobs
jp49rv1l5
Results Ready
Name
efficientnet_lite4
Target Device
- Samsung Galaxy S22 5G
- Android 12
- Snapdragon® 8 Gen 1 | SM8450
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image_tensor: float32[1, 3, 300, 300]Completion Time
7/1/2026, 3:23:27 AM
Versions
- ONNX Runtime: 1.26.0
- QAIRT: v2.45.0.260326154327
- Android: 12 (SP1A.210812.016)
- AI Hub: aihub-2026.06.19.2
Estimated Inference Time
5.52 ms
Estimated Peak Memory Usage
1 ‑ 103 MB
Compute Units
NPU
184
| Stage | Time | Memory |
|---|---|---|
First App Load | 2.36 s | 266‑275 MB |
Subsequent App Load | 344 ms | 58‑160 MB |
Inference | 5.52 ms | 1‑103 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