Profile Job Results
Jobs
jgnx410m5
Results Ready
Name
deepbox_vgg_3d_detection
Target Device
- Snapdragon 7 Gen 4 QRD
- Android 15
- Snapdragon® 7 Gen 4 | SM7750
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: uint16[1, 3, 224, 224]Completion Time
6/13/2026, 1:19:53 PM
Options
--onnx_execution_providers qnnVersions
- ONNX Runtime: 1.25.0
- QAIRT: v2.45.0.260326154327
- Android: 15 (AQ3A.250411.001)
- Build ID: Eliza.LA.1.0.r1-00181-STD.PROD-1
- AI Hub: aihub-2026.06.08.2
Estimated Inference Time
5.17 ms
Estimated Peak Memory Usage
0 ‑ 194 MB
Compute Units
NPU
47
CPU
1
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.76 s | 448‑455 MB |
Subsequent App Load | 329 ms | 13‑212 MB |
Inference | 5.17 ms | 0‑194 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