I asked the question to the benchmarkers the other day, and now they replied:
The situation with the A311D chipsest is quite complex. First of all, there is no way to access its NPU through Android: it doesn’t support Android NN API (NN HAL is missing), there are no custom TensorFlow Lite delegates for this SoC as well as any proprietary SDKs.
Secondly, even when using Linux - you cannot run the standard TF / TFLite models on this platform: you need to compile them using Amlogic’s NPU SDK provided upon a request. It also looks like this NPU is supporting a limited number of TFLite ops and can accelerate INT8 inference only, which means that just some standard quantized image classification models can be executed on it.