News, Releases and More

Starting from version 4.0.4, we release AI Benchmark Nightly builds for ML developers every month.

Compared to the standard version, AI Benchmark Nightly:

• is built with the latest TensorFlow Lite nightly runtime,
• provides support for the full range of TensorFlow ops,
• contains the newest Android TFLite delegates: GPU, NNAPI, Hexagon, Eden and Neuron.

These builds allow ML developers to test their own TFLite models converted with TF-nightly or containing custom TF operators, making it possible to run nearly any TensorFlow model on any mobile device with this benchmark edition.

AI Benchmark Nightly is provided for R&D purpose only and should not be used for benchmarking mobile devices.

You can download the latest AI Benchmark Nightly build from the official website:
https://ai-benchmark.com/download

All questions related to machine learning development for mobile devices can be asked in this thread.

 

What's New:

• TFLite NNAPI, GPU, XNNPACK and Hexagon NN delegates are updated to their latest builds.
• Samsung Eden Delegate is updated to version V2.
• Integrated new MediaTek Neuron Delegate.
• Various bug fixes and performance improvements.

Download this release from the official website or from the Google Play / Huawei AppGallery / Jolla stores.

Feel free to discuss AI Benchmark results in this thread.

Any found issues can be reported here.

 

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.