Profile Job Results
Jobs
jpxnk7x15
Results Ready
Name
mediapipe_face_quantized_FaceDetectorQuantizable
Target Device
- Samsung Galaxy S23
- Android 13
- Snapdragon® 8 Gen 2 | SM8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 3, 256, 256]Completion Time
4/8/2025, 11:33:45 AM
Versions
- ONNX Runtime: 1.21.0+ (commit a46d212)
- QAIRT: v2.32.0.250228225014_116386
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.03.24.0
Estimated Inference Time
480 μs
Estimated Peak Memory Usage
2 ‑ 13 MB
Compute Units
NPU
119
| Stage | Time | Memory |
|---|---|---|
First App Load | 515 ms | 55‑56 MB |
Subsequent App Load | 509 ms | 78‑80 MB |
Inference | 480 μs | 2‑13 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" |
Sign up to run this model on a hosted Qualcomm® device!
Run on device