Profile Job Results
Jobs
jg9xdqvwg
Results Ready
Name
efficientnet_lite4
Target Device
- Dragonwing Q-6690 MTP
- Android 15
- Qualcomm® Dragonwing™ Q-6690 | QCM6690
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image_tensor: uint8[1, 3, 300, 300]Completion Time
7/13/2026, 11:40:04 PM
Options
--onnx_execution_providers qnnVersions
- ONNX Runtime: 1.26.0
- QAIRT: v2.45.0.260326154327
- Android: 15 (AQ3A.250330.001)
- Build ID: QCM6690.LA.1.0.r1-00117-STD.PROD-1
- AI Hub: aihub-2026.07.02.0
Estimated Inference Time
10.9 ms
Estimated Peak Memory Usage
0 ‑ 192 MB
Compute Units
NPU
246
| Stage | Time | Memory |
|---|---|---|
First App Load | 6.01 s | 178‑185 MB |
Subsequent App Load | 390 ms | 67‑260 MB |
Inference | 10.9 ms | 0‑192 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