Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
StateTransformer

Profile Job Results

Jobs
jgjll2rep
Results Ready
Name
statetransformer_float
Target Device
  • QCS8550 (Proxy)
  • Android 12
  • Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
high_res_raster: float32[1, 224, 58, 224]
low_res_raster: float32[1, 224, 58, 224]
context_actions: float32[1, 4, 7]
Completion Time
1/31/2026, 8:20:32 PM
Versions
  • TensorFlow Lite: 2.17.0
  • Android: 14 (UP1A.231005.007)
  • AI Hub: aihub-2026.01.22.0
Estimated Inference Time
577 ms
Estimated Peak Memory Usage
216 ‑ 514 MB
Compute Units
CPU
3062
StageTimeMemory
First App Load
159 ms123‑124 MB
Subsequent App Load
161 ms237‑819 MB
Inference
577 ms216‑514 MB
TensorFlow LiteValue
number_of_threads4
XNNPACK DelegateValue

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

Run on device