Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jgkkdw8ng
Results Ready
Name
efficientnet_lite4
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_tensor: float32[1, 300, 300, 3]
Completion Time
11/14/2026, 11:40:13 PM
Options
--qairt_version latest
Versions
  • Lite RT: 1.4.2
  • QAIRT: v2.51.0.260929181845
  • QNN TfLite Delegate: v2.51.0.260929181845
  • Qualcomm Linux: 1.9-ver.1.0
  • AI Hub: aihub-2026.11.06.1
Estimated Inference Time
4.24 ms
Estimated Peak Memory Usage
0 ‑ 33 MB
Compute Units
NPU
121
StageTimeMemory
First App Load
1.99 s158‑159 MB
Subsequent App Load
212 ms34‑35 MB
Inference
4.24 ms0‑33 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