Llama.cpp Support

#1
by isr431 - opened

Minitron 4b support was just added to llama.cpp, do GGUF quants have to be remade?

Anthracite org

we had merged the PR for these quants, so everything should just work out of the box for you now! we'll update the readme soon to reflect that.

lucyknada changed discussion status to closed

Sign up or log in to comment