Lugh@futurology.todayM to Futurology@futurology.todayEnglish · 1 month agoThis new Chinese AI Is outperforming ChatGPT — and its open-source & runs locallywww.tomsguide.comexternal-linkmessage-square15fedilinkarrow-up161
arrow-up161external-linkThis new Chinese AI Is outperforming ChatGPT — and its open-source & runs locallywww.tomsguide.comLugh@futurology.todayM to Futurology@futurology.todayEnglish · 1 month agomessage-square15fedilink
minus-squareFluffy Kitty Cat@slrpnk.netlinkfedilinkEnglisharrow-up3·1 month agoGiven how memory is the bottleneck especially at the very low end it makes me wonder if one bit quantization of an extremely large model would be a gigabyte per gigabyte of ram better
Given how memory is the bottleneck especially at the very low end it makes me wonder if one bit quantization of an extremely large model would be a gigabyte per gigabyte of ram better