Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
Depth-Anything-V2

Profile Job Results

Jobs
jpy83xq8g
Results Ready
Name
depth_anything_v2
Target Device
  • Dragonwing IQ-9075 EVK
  • Qualcomm Linux 1.9
  • Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: float32[1, 518, 518, 3]
Completion Time
10/4/2026, 3:08:36 AM
Versions
  • Lite RT: 1.4.2
  • QAIRT: v2.50.0.260828221209
  • QNN TfLite Delegate: v2.50.0.260828221209
  • Qualcomm Linux: 1.9-ver.1.0
  • AI Hub: aihub-2026.09.25.0
Estimated Inference Time
48.7 ms
Estimated Peak Memory Usage
1 ‑ 58 MB
Compute Units
NPU
598
StageTimeMemory
First App Load
12.5 s410‑411 MB
Subsequent App Load
254 ms53‑54 MB
Inference
48.7 ms1‑58 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