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

Profile Job Results

Jobs
jprn28095
Results Ready
Name
depth_anything_v3
Target Device
  • Dragonwing IQ-9075 EVK
  • Qualcomm Linux 1.7
  • Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: float32[1, 518, 518, 3]
Completion Time
7/5/2026, 4:35:08 AM
Versions
  • LiteRT: 1.4.4
  • QAIRT: v2.45.0.260326154327
  • QNN TfLite Delegate: v2.45.0.260326154327
  • Qualcomm Linux: 1.7-ver.1.1
  • AI Hub: aihub-2026.06.19.2
Estimated Inference Time
81.5 ms
Estimated Peak Memory Usage
1 ‑ 81 MB
Compute Units
NPU
1051
StageTimeMemory
First App Load
24.2 s591‑592 MB
Subsequent App Load
243 ms75‑77 MB
Inference
81.5 ms1‑81 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