Skip to main content

Indie game storeFree gamesFun gamesHorror games
Game developmentAssetsComics
SalesBundles
Jobs
TagsGame Engines
(1 edit)

What GPU are you using? I'm using the exact same model and quant, It's taking forever for me to load it up via llama.cpp on an RX 7900 XTX and I keep getting an error that it lost connection to the endpoint was lost mid-reply, is there something specific you did, what context size are you using?