Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
NASNet

Profile Job Results

Jobs
jpxd60j1g
Results Ready
Name
nasnet
Target Device
  • QCS8550 (Proxy)
  • Android 12
  • Qualcomm® Dragonwing™ QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image_tensor: float32[1, 331, 331, 3]
Completion Time
7/6/2026, 10:49:48 AM
Versions
  • LiteRT: 1.4.4
  • QAIRT: v2.45.0.260326154327
  • QNN TfLite Delegate: v2.45.0.260326154327
  • Android: 14 (UP1A.231005.007)
  • AI Hub: aihub-2026.06.19.2
Estimated Inference Time
16.6 ms
Estimated Peak Memory Usage
7 ‑ 10 MB
Compute Units
NPU
784
StageTimeMemory
First App Load
11.1 s478‑479 MB
Subsequent App Load
379 ms189‑208 MB
Inference
16.6 ms7‑10 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