Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
GPUNet

Profile Job Results

Jobs
j57vyneq5
Results Ready
Name
gpunet
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, 224, 224, 3]
Completion Time
5/2/2026, 12:41:18 PM
Versions
  • LiteRT: 1.4.3
  • QAIRT: v2.45.0.260326154327
  • QNN TfLite Delegate: v2.45.0.260326154327
  • Android: 14 (UP1A.231005.007)
  • AI Hub: aihub-2026.04.25.0
Estimated Inference Time
903 μs
Estimated Peak Memory Usage
0 ‑ 74 MB
Compute Units
NPU
65
StageTimeMemory
First App Load
952 ms216‑223 MB
Subsequent App Load
179 ms1‑76 MB
Inference
903 μs0‑74 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