Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
EfficientViT-l2-cls

Profile Job Results

Jobs
j5wy62e3g
Results Ready
Name
efficientvit_l2_cls
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, 3, 384, 384]
Completion Time
10/3/2026, 2:10:37 PM
Versions
  • Lite RT: 1.4.2
  • QAIRT: v2.50.0.260828221209
  • QNN TfLite Delegate: v2.50.0.260828221209
  • Qualcomm Linux: 24.04
  • AI Hub: aihub-2026.09.25.0
Estimated Inference Time
18.6 ms
Estimated Peak Memory Usage
0 ‑ 136 MB
Compute Units
NPU
350
StageTimeMemory
First App Load
21.1 s375‑376 MB
Subsequent App Load
444 ms134‑135 MB
Inference
18.6 ms0‑136 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