Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
NASNet

Profile Job Results

Jobs
jpvdjnorp
Results Ready
Name
nasnet
Target Device
  • Samsung Galaxy S24
  • Android 14
  • Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image_tensor: float32[1, 331, 331, 3]
Completion Time
9/5/2026, 2:58:19 PM
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-2026.08.28.1
Estimated Inference Time
12.6 ms
Estimated Peak Memory Usage
0 ‑ 694 MB
Compute Units
NPU
784
StageTimeMemory
First App Load
12.8 s630‑637 MB
Subsequent App Load
286 ms88‑786 MB
Inference
12.6 ms0‑694 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