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

Profile Job Results

Jobs
jgdex3jr5
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
4/8/2025, 5:25:05 PM
Versions
  • TensorFlow Lite: 2.17.0
  • Android: 11 (RP1A.200720.012)
  • AI Hub: aihub-2025.03.24.0
Estimated Inference Time
1.95 ms
Estimated Peak Memory Usage
0 ‑ 3 MB
Compute Units
NPU
39
StageTimeMemory
First App Load
4.32 min0‑3 MB
Subsequent App Load
1.85 min0‑2 MB
Inference
1.95 s0‑3 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