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

Profile Job Results

Jobs
jp3vxy6zg
Results Ready
Name
efficientnet_v2_s
Target Device
  • QCS8550 (Proxy)
  • Android 12
  • Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image_tensor: float32[1, 224, 224, 3]
Completion Time
5/6/2025, 5:53:03 PM
Versions
  • TensorFlow Lite: 2.17.0
  • QAIRT: v2.32.6.250402152434_116405
  • QNN TfLite Delegate: v2.32.6.250402152434_116405
  • Android: 13 (TP1A.220624.014)
  • AI Hub: aihub-2025.05.02.0
Estimated Inference Time
2.67 ms
Estimated Peak Memory Usage
0 ‑ 328 MB
Compute Units
NPU
508
StageTimeMemory
First App Load
2.13 s375‑377 MB
Subsequent App Load
2.13 s399‑401 MB
Inference
2.67 ms0‑328 MB
TensorFlow LiteValue
number_of_threads4
QNN DelegateValue
backend_typekHtpBackend
log_levelkLogLevelWarn
htp_options.performance_modekHtpBurst
htp_options.precisionkHtpFp16
htp_options.useConvHmxtrue

Sign up to run this model on a hosted Qualcomm® device!

Run on device