Profile Job Results
Jobs
jp3wendn5
Results Ready
Name
sam2_encoder
Target Device
- Dragonwing RB3 Gen 2 Vision Kit
- Qualcomm Linux 1.6
- Qualcomm® Dragonwing™ RB3 Gen 2 | QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: uint8[1, 3, 1024, 1024]unnorm_coords: uint8[1, 2, 2]labels: uint8[1, 2]Completion Time
7/7/2026, 2:52:24 AM
Options
--onnx_execution_providers qnnVersions
- ONNX Runtime: 1.26.0
- QAIRT: v2.45.0.260326154327
- Qualcomm Linux: 1.6-ver.1.2
- AI Hub: aihub-2026.07.02.0
Estimated Inference Time
676 ms
Estimated Peak Memory Usage
6 ‑ 12 MB
Compute Units
NPU
444
| Stage | Time | Memory |
|---|---|---|
First App Load | 5.39 min | 2 GB |
Subsequent App Load | 781 ms | 64‑65 MB |
Inference | 676 ms | 6‑12 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