Played around with a tiny 1.5b deepseek model, it was thinking for a loooong while before finally answering my question.
By then it had completely forgotten what the original question was and had instead hallucinated a new question which it then gave me an answer for
sure, you can run them on a phone, a laptop even a raspberry pi. depending on what size and speed you want of course
Played around with a tiny 1.5b deepseek model, it was thinking for a loooong while before finally answering my question.
By then it had completely forgotten what the original question was and had instead hallucinated a new question which it then gave me an answer for
I give it a perfect 7/10
yeah I wouldn’t bother with anything below 4-7b for this exact reason.