Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
3D-Deep-BOX

Profile Job Results

Jobs
jp3qnq9z5
Results Ready
Name
deepbox_vgg_3d_detection
Target Device
  • QCS8550 (Proxy)
  • Android 12
  • Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: float32[1, 224, 224, 3]
Completion Time
5/3/2026, 5:01:00 AM
Versions
  • LiteRT: 1.4.3
  • QAIRT: v2.45.0.260326154327
  • QNN TfLite Delegate: v2.45.0.260326154327
  • Android: 14 (UP1A.231005.007)
  • AI Hub: aihub-2026.04.25.0
Estimated Inference Time
5.14 ms
Estimated Peak Memory Usage
0 ‑ 3 MB
Compute Units
NPU
42
StageTimeMemory
First App Load
1.38 s340‑341 MB
Subsequent App Load
274 ms0‑209 MB
Inference
5.14 ms0‑3 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