Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jp1m7q2np
Results Ready
Name
wedetect_detector
Target Device
  • Arduino VENTUNO Q
  • Ubuntu 24.04
  • Qualcomm® Dragonwing™ IQ-8275 | QCS8275
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: float32[1, 3, 640, 640]
txt_feats: float32[1, 80, 768]
Completion Time
11/15/2026, 10:39:36 AM
Options
--qairt_version latest
Versions
  • Lite RT: 1.4.2
  • QAIRT: v2.51.0.260929181845
  • QNN TfLite Delegate: v2.51.0.260929181845
  • Qualcomm Linux: 24.04
  • AI Hub: aihub-2026.11.06.1
Estimated Inference Time
35.0 ms
Estimated Peak Memory Usage
0 ‑ 84 MB
Compute Units
NPU
624
StageTimeMemory
First App Load
10.8 s299‑300 MB
Subsequent App Load
278 ms79‑80 MB
Inference
35.0 ms0‑84 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