I hear its easy, but I’ve had no luck at all on the most distilled models (for prelim testing), and am wondering how things have broken so badly.
Comment on US Bill proposed to jail people who download Deepseek
Knock_Knock_Lemmy_In@lemmy.world 2 months agoIt’s easy to run a distilled version of the R1 model locally. It’s very difficult to run the full version. Min $6k to get 7 tokens per second.
Kyuuketsuki@lemmy.ml 2 months ago
rumba@lemmy.zip 2 months ago