matrix07012 @matrix@gameliberty.club

@mint @VD15 @waifu Logically IO is a massive bottleneck since it's a bunch of small calculations over a large dataset

Fern would enjoy this

@waifu @VD15 LLammaCPP can split the model between your GPU and CPU so you can maybe run 1-2 layers on your GPU and rest on your CPU. With a quantized (https://huggingface.co/TheBloke/Silicon-Maid-7B-GGUF) small model it shouldn't be super slow.

@sjw

@burner who?