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

Profile Job Results

Jobs
jgnkz4mjg
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
8/8/2026, 12:40:51 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-2026.07.31.1
Estimated Inference Time
21.4 ms
Estimated Peak Memory Usage
0 ‑ 136 MB
Compute Units
NPU
350
StageTimeMemory
First App Load
25.3 s435‑436 MB
Subsequent App Load
325 ms134‑135 MB
Inference
21.4 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