Profile Job Results
Jobs
jgj1jve1g
Results Ready
Name
nafnet_deblur
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: uint16[1, 3, 360, 640]Completion Time
6/14/2026, 12:38:44 AM
Versions
- ONNX Runtime: 1.25.0
- QAIRT: v2.45.0.260326154327
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.06.08.2
Estimated Inference Time
89.7 ms
Estimated Peak Memory Usage
0 ‑ 84 MB
Compute Units
NPU
674
| Stage | Time | Memory |
|---|---|---|
First App Load | 36.8 s | 1 GB |
Subsequent App Load | 688 ms | 0‑483 MB |
Inference | 89.7 ms | 0‑84 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