Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
Facial-Landmark-Detection

Profile Job Results

Jobs
jpr270n75
Results Ready
Name
facemap_3dmm
Target Device
  • QCS8250 (Proxy)
  • Android 12
  • Qualcomm® QCS8250
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 128, 128, 3]
Completion Time
9/14/2025, 7:28:24 AM
Versions
  • TensorFlow Lite: 2.17.0
  • Android: 11 (RP1A.200720.012)
  • AI Hub: aihub-2025.09.05.0
Estimated Inference Time
1.89 ms
Estimated Peak Memory Usage
0 ‑ 11 MB
Compute Units
NPU
40
StageTimeMemory
First App Load
251 ms0‑11 MB
Subsequent App Load
87.8 ms0‑11 MB
Inference
1.89 ms0‑11 MB
TensorFlow LiteValue
number_of_threads4
NNAPI DelegateValue
accelerator_name"qti-dsp"
execution_preferencekSustainedSpeed
allow_fp16true

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

Run on device