Profile Job Results
Jobs
jp8mv8e85
Results Ready
Name
mediapipe_pose_w8a8_PoseLandmarkDetector
Target Device
- QCS8250 (Proxy)
- Android 12
- Qualcomm® QCS8250
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 3, 256, 256]Completion Time
10/5/2025, 12:49:54 AM
Options
--qairt_version 2.37Versions
- ONNX Runtime: 1.22.2
- Android: 11 (RP1A.200720.012)
- AI Hub: aihub-2025.09.26.0
Estimated Inference Time
13.0 ms
Estimated Peak Memory Usage
8 ‑ 14 MB
Compute Units
CPU
397
| Stage | Time | Memory |
|---|---|---|
First App Load | 191 ms | 16‑18 MB |
Subsequent App Load | 240 ms | 10‑13 MB |
Inference | 13.0 ms | 8‑14 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 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device