Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jpen20q7p
Results Ready
Name
efficientnet_lite4
Target Device
  • Dragonwing Q-6690 MTP
  • Android 15
  • Qualcomm® Dragonwing™ Q-6690 | QCM6690
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image_tensor: uint8[1, 300, 300, 3]
Completion Time
11/14/2026, 11:48:56 PM
Options
--qairt_version latest
Versions
  • Lite RT: 1.4.2
  • QAIRT: v2.51.0.260929181845
  • QNN TfLite Delegate: v2.51.0.260929181845
  • Android: 15 (AQ3A.250330.001)
  • Build ID: QCM6690.LA.1.0.r1-00117-STD.PROD-1
  • AI Hub: aihub-2026.11.06.1
Estimated Inference Time
10.1 ms
Estimated Peak Memory Usage
0 ‑ 175 MB
Compute Units
NPU
123
StageTimeMemory
First App Load
4.71 s237‑244 MB
Subsequent App Load
222 ms14‑193 MB
Inference
10.1 ms0‑175 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