misk@sopuli.xyz to Technology@beehaw.org · 1 month agoDeepSeek-V3 now runs at 20 tokens per second on Mac Studio, and that’s a nightmare for OpenAIventurebeat.comexternal-linkmessage-square25fedilinkarrow-up1140arrow-down10cross-posted to: [email protected]
arrow-up1140arrow-down1external-linkDeepSeek-V3 now runs at 20 tokens per second on Mac Studio, and that’s a nightmare for OpenAIventurebeat.commisk@sopuli.xyz to Technology@beehaw.org · 1 month agomessage-square25fedilinkcross-posted to: [email protected]
minus-squarevintageballs@feddit.orglinkfedilinkDeutscharrow-up1·29 days agoThey probably confused the R1 Qwen distill with something else. Afaik there is no 32b model from DeepSeek directly.
They probably confused the R1 Qwen distill with something else. Afaik there is no 32b model from DeepSeek directly.