Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
VIT

Profile Job Results

Jobs
j574d9rv5
Results Ready
Name
vit
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, 224, 224, 3]
Completion Time
8/22/2026, 8:35:52 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
13.0 ms
Estimated Peak Memory Usage
0 ‑ 173 MB
Compute Units
NPU
535
StageTimeMemory
First App Load
6.71 s479‑480 MB
Subsequent App Load
506 ms172‑173 MB
Inference
13.0 ms0‑173 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