Profile Job Results
Jobs
jp8ze8wop
Results Ready
Name
mediapipe_face_w8a8_FaceLandmarkDetector
Target Device
- Samsung Galaxy S24
- Android 14
- Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 3, 192, 192]Completion Time
11/30/2025, 8:52:40 AM
Options
--qairt_version 2.37Versions
- ONNX Runtime: 1.23.0
- QAIRT: v2.37.1.250807093845_124904
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2025.11.18.0
Estimated Inference Time
263 μs
Estimated Peak Memory Usage
0 ‑ 30 MB
Compute Units
NPU
106
CPU
1
| Stage | Time | Memory |
|---|---|---|
First App Load | 490 ms | 105‑112 MB |
Subsequent App Load | 459 ms | 100‑212 MB |
Inference | 263 μs | 0‑30 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