[ta988]

You will have to explain to me how.

[bmelton]

https://digitalspaceport.com/how-to-run-deepseek-r1-671b-ful...

[muricula]

Is that a CPU based inference build? Shouldn't you be able to get more performance out of the M3's GPU?

[wmf]

Inference is about memory bandwidth and some CPUs have just as much bandwidth as a GPU.

[radlad]

https://news.ycombinator.com/item?id=42897205