▲ 141 ▼ DeepSeek-V3 now runs at 20 tokens per second on Mac Studio, and that’s a nightmare for OpenAI (venturebeat.com) submitted 1 year ago by misk@sopuli.xyz to c/technology@beehaw.org 25 comments fedilink hide all child comments
[–] morrowind@lemmy.ml 5 points 1 year ago* (1 child) The hell is v3 32b. Are you talking about a distill permalink fedilink source parent hideshow 2 child comments replies: [–] vintageballs@feddit.org 1 point 1 year ago They probably confused the R1 Qwen distill with something else. Afaik there is no 32b model from DeepSeek directly. permalink fedilink source parent
[–] vintageballs@feddit.org 1 point 1 year ago They probably confused the R1 Qwen distill with something else. Afaik there is no 32b model from DeepSeek directly. permalink fedilink source parent