Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
MediaPipe-Face-Detection-Quantized

Profile Job Results

Jobs
jg9jl3dl5
Results Ready
Name
mediapipe_face_quantized_FaceLandmarkDetectorQuantizable
Target Device
  • QCS6490 (Proxy)
  • Android 12
  • Qualcomm® QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 192, 192, 3]
Completion Time
4/8/2025, 11:32:47 AM
Versions
  • QAIRT: v2.32.0.250228225014_116386
  • QNN Backend API: 5.32.0
  • QNN Core API: 2.24.0
  • Android: 12 (SP1A.210812.016)
  • AI Hub: aihub-2025.03.24.0
Estimated Inference Time
392 ms
Estimated Peak Memory Usage
0 ‑ 15 MB
Compute Units
NPU
112
StageTimeMemory
First App Load
2.63 min0‑7 MB
Subsequent App Load
2.48 min0‑14 MB
Inference
392 ms0‑15 MB
QNNValue
context_options.htp_options.performance_modeBURST
default_graph_options.htp_options.precisionFLOAT16

Sign up to run this model on a hosted Qualcomm® device!

Run on device