Profile Job Results
Jobs
jgo4n7945
Results Ready
Name
efficientnet_b4
Target Device
- Snapdragon 7 Gen 4 QRD
- Android 15
- Snapdragon® 7 Gen 4 | SM7750
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image_tensor: uint16[1, 3, 380, 380]Completion Time
7/6/2026, 6:20:57 PM
Options
--onnx_execution_providers qnnVersions
- ONNX Runtime: 1.26.0
- QAIRT: v2.45.0.260326154327
- Android: 15 (AQ3A.250411.001)
- Build ID: Eliza.LA.1.0.r1-00181-STD.PROD-1
- AI Hub: aihub-2026.06.19.2
Estimated Inference Time
9.11 ms
Estimated Peak Memory Usage
1 ‑ 289 MB
Compute Units
NPU
483
| Stage | Time | Memory |
|---|---|---|
First App Load | 12.8 s | 298‑305 MB |
Subsequent App Load | 222 ms | 0‑290 MB |
Inference | 9.11 ms | 1‑289 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 | "0" |
| 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