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

Profile Job Results

Jobs
jgde6z8z5
Results Ready
Name
ffnet_78s
Target Device
  • QCS8250 (Proxy)
  • Android 12
  • Qualcomm® QCS8250
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 1024, 2048, 3]
Completion Time
5/21/2025, 2:08:39 AM
Versions
  • TensorFlow Lite: 2.17.0
  • Android: 11 (RP1A.200720.012)
  • AI Hub: aihub-2025.05.14.0
Estimated Inference Time
338 ms
Estimated Peak Memory Usage
1 ‑ 12 MB
Compute Units
NPU
153
StageTimeMemory
First App Load
1.66 s3‑13 MB
Subsequent App Load
1.37 s1‑13 MB
Inference
338 ms1‑12 MB
TensorFlow LiteValue
number_of_threads4
NNAPI DelegateValue
accelerator_name"qti-dsp"
execution_preferencekSustainedSpeed
allow_fp16true

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

Run on device