misk ( misk@sopuli.xyz ) to Technology · 2 years agoDeepSeek-V3 now runs at 20 tokens per second on Mac Studio, and that’s a nightmare for OpenAIventurebeat.comexternal-linkmessage-square25linkfedilinkarrow-up1141
arrow-up1141external-linkDeepSeek-V3 now runs at 20 tokens per second on Mac Studio, and that’s a nightmare for OpenAIventurebeat.commisk ( misk@sopuli.xyz ) to Technology · 2 years agomessage-square25linkfedilink
minus-squareMniot ( Mniot@programming.dev ) linkfedilinkEnglisharrow-up4·2 years agoNot an answer to your question, but I thought this was a nice article for getting some basic grounding on the new AI stuff: https://arstechnica.com/science/2023/07/a-jargon-free-explanation-of-how-ai-large-language-models-work/
Not an answer to your question, but I thought this was a nice article for getting some basic grounding on the new AI stuff: https://arstechnica.com/science/2023/07/a-jargon-free-explanation-of-how-ai-large-language-models-work/