Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
Depth-Anything-V3

Profile Job Results

Jobs
jp4er892g
Results Ready
Name
depth_anything_v3
Target Device
  • Samsung Galaxy S22 5G
  • Android 12
  • Snapdragon® 8 Gen 1 | SM8450
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: float32[1, 518, 518, 3]
Completion Time
10/3/2026, 8:37:42 PM
Versions
  • Lite RT: 1.4.2
  • QAIRT: v2.50.0.260828221209
  • QNN TfLite Delegate: v2.50.0.260828221209
  • Android: 12 (SP1A.210812.016)
  • AI Hub: aihub-2026.09.25.0
Estimated Inference Time
106 ms
Estimated Peak Memory Usage
1 ‑ 550 MB
Compute Units
NPU
1054
StageTimeMemory
First App Load
9.80 s645‑654 MB
Subsequent App Load
298 ms73‑623 MB
Inference
106 ms1‑550 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