Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
Midas-V2-Quantized

Profile Job Results

Jobs
j57yk03v5
Results Ready
Name
midas_quantized
Target Device
  • QCS8250 (Proxy)
  • Android 12
  • Qualcomm® QCS8250
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
image: uint8[1, 256, 256, 3]
Completion Time
11/26/2024, 12:10:51 PM
Versions
  • TensorFlow Lite: 2.17.0
  • Android: 11 (RP1A.200720.012)
  • AI Hub: aihub-2024.11.22.0
Estimated Inference Time
15.6 ms
Estimated Peak Memory Usage
0 ‑ 5 MB
Compute Units
NPU
145
StageTimeMemory
First App Load
610 ms3‑4 MB
Subsequent App Load
330 ms1‑5 MB
Inference
15.6 ms0‑5 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