Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
Unet-Segmentation

Profile Job Results

Jobs
jpv7220zp
Results Ready
Name
unet_segmentation
Target Device
  • Arduino VENTUNO Q
  • Ubuntu 24.04
  • Qualcomm® Dragonwing™ IQ-8275 | QCS8275
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: uint8[1, 640, 1280, 3]
Completion Time
8/9/2026, 4:03:15 AM
Versions
  • Lite RT: 1.4.5
  • QAIRT: v2.45.0.260326154327
  • QNN TfLite Delegate: v2.45.0.260326154327
  • Qualcomm Linux: 24.04
  • AI Hub: aihub-2026.07.31.1
Estimated Inference Time
37.2 ms
Estimated Peak Memory Usage
2 ‑ 39 MB
Compute Units
NPU
37
StageTimeMemory
First App Load
4.95 s343 MB
Subsequent App Load
234 ms36 MB
Inference
37.2 ms2‑39 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