Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
Inception-v3

Profile Job Results

Jobs
jp2w2nm6p
Results Ready
Name
inception_v3
Target Device
  • QCS8550 (Proxy)
  • Android 12
  • Qualcomm® Dragonwing™ QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image_tensor: uint8[1, 299, 299, 3]
Completion Time
9/5/2026, 8:06:15 PM
Versions
  • Lite RT: 1.4.5
  • QAIRT: v2.45.0.260326154327
  • QNN TfLite Delegate: v2.45.0.260326154327
  • Android: 13 (TP1A.220624.014)
  • AI Hub: aihub-2026.08.28.1
Estimated Inference Time
908 μs
Estimated Peak Memory Usage
0 ‑ 31 MB
Compute Units
NPU
144
StageTimeMemory
First App Load
778 ms105‑106 MB
Subsequent App Load
221 ms24‑60 MB
Inference
908 μs0‑31 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