News for hackers. Stuff that matters.
Re:I'm making LLMs work on small and old devices by mrashad74 on Thursday November 12, 2026 @01:57PM (#50472342)
A year ago 1B parameter models couldn't do much, today with the correct harness and/or fine-tuning they can do more or less serious work (not frontier tho).

I believe in a 6-8 months it will get even better and my TV will be happy.

I didn't try fine tuning so small models honestly but looks interesitng to try.

Re:I'm making LLMs work on small and old devices by BoredomIsFun on Friday November 13, 2026 @05:39AM (#50481480)
Not sure about 1b but 2.5 years old gemma 2 2B was very capable and useful model I used for summarizing aricles then.