ae_dataviz@alien.topB to LocalLLaMAEnglish · 1 year agoQuantizing 70b models to 4-bit, how much does performance degrade?plus-squaremessage-squaremessage-square22fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1message-squareQuantizing 70b models to 4-bit, how much does performance degrade?plus-squareae_dataviz@alien.topB to LocalLLaMAEnglish · 1 year agomessage-square22fedilink