Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
FFNet-78S-LowRes

Profile Job Results

Jobs
jpxnk4n85
Results Ready
Name
ffnet_78s_lowres
Target Device
  • SA8255 (Proxy)
  • Android 13
  • Qualcomm® SA8255P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: float32[1, 512, 1024, 3]
Completion Time
4/8/2025, 4:43:22 PM
Versions
  • TensorFlow Lite: 2.17.0
  • QAIRT: v2.32.0.250228225014_116386
  • QNN TfLite Delegate: v2.32.0.250228225014_116386
  • Android: 13 (TP1A.220624.014)
  • AI Hub: aihub-2025.03.24.0
Estimated Inference Time
13.1 s
Estimated Peak Memory Usage
1 ‑ 18 MB
Compute Units
NPU
151
StageTimeMemory
First App Load
47.7 min369‑370 MB
Subsequent App Load
50.4 min388‑390 MB
Inference
13.1 s1‑18 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