logoalt Hacker News

dannywyesterday at 5:53 PM3 repliesview on HN

I’m running the same model on a 48GB MBP with a q4 quant and it’s pretty decent. You definitely don’t 128GB. That’s the scale for 70B models at q8 or something.


Replies

dom96yesterday at 6:26 PM

I've been running it on my 48GB MBP too and it's not particularly great. Super slow and not near enough to the quality provided by even Claude Sonnet.

doodlesdevyesterday at 6:06 PM

How much does one of those cost in the US? Here in Brazil, your notebook is worth as much as a used Honda Fit, which seems absolutely insane. For comparison, the ThinkPad I'm currently running cost me 1/20 of how much this MBP costs here, leaving me with over $8.000 to spend with LLM inference (if I actually spent money with that).

show 1 reply
DrammBAtoday at 4:02 AM

> I’m running the same model on a 48GB MBP with a q4 quant and it’s pretty decent.

Context size?