Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
Segformer-Base

Profile Job Results

Jobs
jpey6yd75
Results Ready
Name
segformer_base
Target Device
  • QCS8550 (Proxy)
  • Android 12
  • Qualcomm® Dragonwing™ QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: float32[1, 512, 512, 3]
Completion Time
8/9/2026, 1:30:02 AM
Versions
  • Lite RT: 1.4.5
  • QAIRT: v2.45.0.260326154327
  • QNN TfLite Delegate: v2.45.0.260326154327
  • Android: 14 (UP1A.231005.007)
  • AI Hub: aihub-2026.07.31.1
Estimated Inference Time
22.7 ms
Estimated Peak Memory Usage
8 ‑ 12 MB
Compute Units
NPU
538
StageTimeMemory
First App Load
2.20 s149‑150 MB
Subsequent App Load
203 ms9‑16 MB
Inference
22.7 ms8‑12 MB
Lite RTValue
number_of_threads4
QNN DelegateValue
backend_typekHtpBackend
log_levelkLogLevelWarn
htp_options.performance_modekHtpBurst
htp_options.precisionkHtpFp16
htp_options.optimization_strategykHtpOptimizeForInferenceO3
htp_options.useConvHmxtrue

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

Run on device