AI Benchmark 4.0.3 Mobile Released

What's New:
  • TFLite XNNPACK delegate is now enabled by default for CPU inference.
  • Updated Qualcomm Hexagon NN and Samsung Eden NN libraries.
  • GPU acceleration is now available for quantized neural networks.
  • Various enhancements and performance improvements.

Download this release from the Google Play: link

Feel free to discuss AI Benchmark results in this thread.

Any found issues can be reported here.
 
Top