Profile Job Results
Jobs
jp1d7v8lp
Results Ready
Name
mediapipe_pose_pose_landmark_detector
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
Target Model
Input Specs
image: uint8[1, 256, 256, 3]Completion Time
4/5/2026, 7:38:41 AM
Options
--qairt_version 2.42Versions
- ONNX Runtime: 1.24.3
- QAIRT: v2.42.0.251225135753_193295
- Qualcomm Linux: 1.6-ver.1.2
- AI Hub: aihub-2026.03.29.0
Estimated Inference Time
1.25 ms
Estimated Peak Memory Usage
0 ‑ 3 MB
Compute Units
NPU
293
| Stage | Time | Memory |
|---|---|---|
First App Load | 200 ms | 10‑11 MB |
Subsequent App Load | 188 ms | 12‑13 MB |
Inference | 1.25 ms | 0‑3 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 | "2" |
| 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