Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
FFNet-122NS-LowRes

Profile Job Results

Jobs
jgnlo4rm5
Results Ready
Name
ffnet_122ns_lowres
Target Device
  • QCS6490 (Proxy)
  • Android 12
  • Qualcomm® QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 512, 1024, 3]
Completion Time
5/6/2025, 4:37:10 PM
Versions
  • TensorFlow Lite: 2.17.0
  • QAIRT: v2.32.6.250402152434_116405
  • QNN TfLite Delegate: v2.32.6.250402152434_116405
  • Android: 12 (SP1A.210812.016)
  • AI Hub: aihub-2025.05.02.0
Estimated Inference Time
9.32 ms
Estimated Peak Memory Usage
0 ‑ 68 MB
Compute Units
NPU
220
StageTimeMemory
First App Load
2.23 s174‑180 MB
Subsequent App Load
2.29 s178‑255 MB
Inference
9.32 ms0‑68 MB
TensorFlow LiteValue
number_of_threads4
QNN DelegateValue
backend_typekHtpBackend
log_levelkLogLevelWarn
htp_options.performance_modekHtpBurst
htp_options.precisionkHtpFp16
htp_options.useConvHmxtrue

Sign up to run this model on a hosted Qualcomm® device!

Run on device