minus-squarevintageballs@feddit.orgtoTechnology@beehaw.org•DeepSeek-V3 now runs at 20 tokens per second on Mac Studio, and that’s a nightmare for OpenAIlinkfedilinkDeutscharrow-up1·20 days agoThey probably confused the R1 Qwen distill with something else. Afaik there is no 32b model from DeepSeek directly. linkfedilink
They probably confused the R1 Qwen distill with something else. Afaik there is no 32b model from DeepSeek directly.