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

Profile Job Results

Jobs
jp13r4o25
Results Ready
Name
face_det_lite
Target Device
  • Dragonwing Q-6690 MTP
  • Android 15
  • Qualcomm® Dragonwing™ Q-6690 | QCM6690
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input: uint8[1, 480, 640, 1]
Completion Time
6/14/2026, 1:00:59 AM
Versions
  • LiteRT: 1.4.4
  • QAIRT: v2.45.0.260326154327
  • QNN TfLite Delegate: v2.45.0.260326154327
  • Android: 15 (AQ3A.250330.001)
  • Build ID: QCM6690.LA.1.0.r1-00117-STD.PROD-1
  • AI Hub: aihub-2026.06.08.2
Estimated Inference Time
2.72 ms
Estimated Peak Memory Usage
0 ‑ 137 MB
Compute Units
NPU
90
StageTimeMemory
First App Load
1.39 s153‑161 MB
Subsequent App Load
197 ms0‑139 MB
Inference
2.72 ms0‑137 MB
Lite RTValue
number_of_threads4
QNN DelegateValue
backend_typekHtpBackend
log_levelkLogLevelWarn
htp_options.performance_modekHtpBurst
htp_options.precisionkHtpFp16
htp_options.optimization_strategykHtpOptimizeForInferenceO3
htp_options.useConvHmxtrue

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

Run on device