Profile Job Results
Jobs
jgk6ze0o5
Results Ready
Name
u2net_segmentation
Target Device
- Snapdragon 8 Elite Gen 6 QRD
- Android 17
- Snapdragon® 8 Elite Gen 6 | SM8950
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: float32[1, 3, 320, 320]Completion Time
10/20/2026, 8:45:14 AM
Options
--qairt_version 2.50Versions
- ONNX Runtime: 1.30.0
- QNN Execution Provider: 2.5.0
- QAIRT: v2.50.0.260828221209
- Android: 17 (CQ2A.260820.002-CP2A.260605.016)
- Build ID: Maili.LA.1.0.r1-00252-STD.PROD-1
- AI Hub: aihub-2026.10.10.0
Estimated Inference Time
7.99 ms
Estimated Peak Memory Usage
2 ‑ 194 MB
Compute Units
NPU
376
| Stage | Time | Memory |
|---|---|---|
First App Load | 3.79 s | 456‑463 MB |
Subsequent App Load | 187 ms | 87‑280 MB |
Inference | 7.99 ms | 2‑194 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 | "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