Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
TrOCR

Profile Job Results

Jobs
jgke1djwg
Results Ready
Name
trocr_TrOCREncoder
Target Device
  • SA8650 (Proxy)
  • Android 13
  • Qualcomm® SA8650P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
pixel_values: float32[1, 384, 384, 3]
Completion Time
1/8/2025, 2:07:56 AM
Versions
  • QNN: v2.28.2.241116104011_103376
  • QNN Backend API: 5.28.0
  • QNN Core API: 2.21.0
  • Android: 13 (TP1A.220624.014)
  • AI Hub: aihub-2025.01.04.0
Estimated Inference Time
37.5 ms
Estimated Peak Memory Usage
2 ‑ 4 MB
Compute Units
NPU
443
StageTimeMemory
First App Load
215 ms1‑2 MB
Subsequent App Load
187 ms1‑2 MB
Inference
37.5 ms2‑4 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