kettyful

> Yes it does work with DirectML version of DFL. However the existing bundle of DirectML is using an older version of Tensorflow, which has a poorer performance. > >...

Your version - ~550ms +/- 10 - AMP model res 384 dims 128 CUDA version - ~604 + 100 - AMP model res 384 dims 128 Directx12 V - ~570...

Pretty sure that's because it shows free vram so what's not being used by windows. You might have to run it on a linux system to use all your vram.