minus-squarenhbis0n@alien.topBtoLocalLLaMA@poweruser.forum•llama2 13B on Gtx 1070linkfedilinkEnglisharrow-up1·1 year agoI run 7B’s on my 1070. ollama run llama2 produces between 20 and 30 tokens per second in ubuntu. linkfedilink
nhbis0n@alien.topB to LocalLLaMA@poweruser.forumEnglish · 1 year agoM3 Proplus-squaremessage-squaremessage-square0fedilinkarrow-up11arrow-down10
arrow-up11arrow-down1message-squareM3 Proplus-squarenhbis0n@alien.topB to LocalLLaMA@poweruser.forumEnglish · 1 year agomessage-square0fedilink
minus-squarenhbis0n@alien.topBtoLocalLLaMA@poweruser.forum•OpenAI announces leadership transition: Sama no longer CEOlinkfedilinkEnglisharrow-up1·1 year agoDid the AI coordinate his sacking? linkfedilink
I run 7B’s on my 1070. ollama run llama2 produces between 20 and 30 tokens per second in ubuntu.