Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
EfficientNet-V2-s

Profile Job Results

Jobs
jp39m9dzp
Results Ready
Name
efficientnet_v2_s
Target Device
  • Arduino VENTUNO Q
  • Ubuntu 24.04
  • Qualcomm® Dragonwing™ IQ-8275 | QCS8275
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image_tensor: float32[1, 384, 384, 3]
Completion Time
8/22/2026, 9:46:10 PM
Versions
  • Lite RT: 1.4.5
  • QAIRT: v2.45.0.260326154327
  • QNN TfLite Delegate: v2.45.0.260326154327
  • Qualcomm Linux: 24.04
  • AI Hub: aihub-2026.08.14.0
Estimated Inference Time
8.20 ms
Estimated Peak Memory Usage
0 ‑ 52 MB
Compute Units
NPU
508
StageTimeMemory
First App Load
5.17 s205‑206 MB
Subsequent App Load
307 ms50 MB
Inference
8.20 ms0‑52 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