Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
HRNet-W48-OCR

Profile Job Results

Jobs
jp1w0re2g
Results Ready
Name
hrnet_w48_ocr
Target Device
  • SA8775P ADP
  • Android 14
  • Qualcomm® SA8775P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 1024, 2048, 3]
Completion Time
9/28/2025, 5:39:21 AM
Versions
  • TensorFlow Lite: 2.17.0
  • Android: 14 (UQ1A.240205.002)
  • Build ID: Snapdragon_Auto.HQX.4.5.6.0.r2-00011-STD.PROD-1.89321.2
  • AI Hub: aihub-2025.09.23.1
Estimated Inference Time
19.9 s
Estimated Peak Memory Usage
4 ‑ 324 MB
Compute Units
CPU
579
StageTimeMemory
First App Load
41.4 s2 GB
Subsequent App Load
5.87 s2‑3 GB
Inference
19.9 s4‑324 MB
TensorFlow LiteValue
number_of_threads4
XNNPACK DelegateValue

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

Run on device