Re:The Illustrated DeepSeek-R1
by itissid on Tuesday January 28, 2025 @01:57AM
(#42849607)
I am using the 32Gb distilled model on my local 3090 with Continue in VSCode. It beats everything out of the water.
[ Parent
| on HN ]
Re:The Illustrated DeepSeek-R1
by dontwearitout on Tuesday January 28, 2025 @02:08AM
(#42849658)
How many tokens/s do you get on a 3090? With the extra tokens for the internal monologue, is it still performant enough for smooth VSCode integration?
Re:The Illustrated DeepSeek-R1
by MarcelOlsz on Tuesday January 28, 2025 @10:30AM
(#42853439)
Any idea how to use a cloud hosted version with cursor?