News for hackers. Stuff that matters.
Re:DeepSeek-R1 with Dynamic 1.58-bit Quantization by diggan on Tuesday January 28, 2025 @08:25AM (#42852018)
> Can I use that on the train though? I can with a 128GB MacBook, without it sounding like a helicopter taking off as well.

What kind of timescale do you expect to be able to train a useful LLM with that?

Re:DeepSeek-R1 with Dynamic 1.58-bit Quantization by orf on Tuesday January 28, 2025 @10:01AM (#42853081)
Well it’s about an hour to commute on the train so I guess that long :3