Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
FFNet-40S-Quantized

Profile Job Results

Jobs
jnp1m36lp
Results Ready
Name
ffnet_40s_quantized
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
8/27/2024, 10:11:11 AM
Versions
  • TensorFlow Lite: 2.16.1
  • Android: 11 (RP1A.200720.012)
  • AI Hub: aihub-2024.08.23.0
Estimated Inference Time
188 ms
Estimated Peak Memory Usage
1 - 7 MB
Compute Units
NPU
99
StageTimeMemory
First App Load
532 ms1-3 MB
Subsequent App Load
219 ms1-3 MB
Inference
188 ms1-7 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