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

Profile Job Results

Jobs
jgo206eqp
Results Ready
Name
face_det_lite_quantized
Target Device
  • QCS6490 (Proxy)
  • Android 12
  • Qualcomm® QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
input: uint8[1, 480, 640, 1]
Completion Time
1/21/2025, 3:29:40 PM
Versions
  • QNN: v2.28.2.241116104011_103376
  • QNN Backend API: 5.28.0
  • QNN Core API: 2.21.0
  • Android: 12 (SP1A.210812.016)
  • AI Hub: aihub-2025.01.04.0
Estimated Inference Time
1.04 ms
Estimated Peak Memory Usage
0 ‑ 12 MB
Compute Units
NPU
122
StageTimeMemory
First App Load
155 ms0‑11 MB
Subsequent App Load
141 ms0‑12 MB
Inference
1.04 ms0‑12 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