Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
DeepLabV3-Plus-MobileNet

Profile Job Results

Jobs
jgkrvrzw5
Results Ready
Name
deeplabv3_plus_mobilenet
Target Device
  • QCS8450 (Proxy)
  • Android 13
  • Qualcomm® QCS8450
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: float32[1, 520, 520, 3]
Completion Time
5/3/2026, 5:18:57 AM
Versions
  • LiteRT: 1.4.3
  • QAIRT: v2.45.0.260326154327
  • QNN TfLite Delegate: v2.45.0.260326154327
  • Android: 13 (TP1A.220624.014)
  • AI Hub: aihub-2026.04.25.0
Estimated Inference Time
19.9 ms
Estimated Peak Memory Usage
0 ‑ 213 MB
Compute Units
NPU
98
StageTimeMemory
First App Load
2.08 s216‑225 MB
Subsequent App Load
178 ms1‑215 MB
Inference
19.9 ms0‑213 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