🇦🇺𝕄𝕦𝕟𝕥𝕖𝕕𝕔𝕣𝕠𝕔𝕕𝕚𝕝𝕖@lemm.ee to LocalLLaMA@sh.itjust.worksEnglish · 6 days agoHow much gpu do i need to run a 90b modelmessage-squaremessage-square16fedilinkarrow-up113arrow-down11file-text
arrow-up112arrow-down1message-squareHow much gpu do i need to run a 90b model🇦🇺𝕄𝕦𝕟𝕥𝕖𝕕𝕔𝕣𝕠𝕔𝕕𝕚𝕝𝕖@lemm.ee to LocalLLaMA@sh.itjust.worksEnglish · 6 days agomessage-square16fedilinkfile-text
minus-squarered@lemmy.ziplinkfedilinkEnglisharrow-up1·5 days agothis is useless, llama.cpp already does that airllm does (offloading to CPU) but its actually faster. so just use ollama
this is useless, llama.cpp already does that airllm does (offloading to CPU) but its actually faster. so just use ollama