Hacker News new | ask | show | jobs
by 0cf8612b2e1e 814 days ago
At this point, I cannot run an entire class of models without OOM. I will take a performance hit if it lets me run it at all.

I want a consumer card that can do some number of tokens per second. I do not need a monster that can serve as the basis for a startup.
1 comments
hnfong 813 days ago
A maxed out Mac Studio probably fits your requirements as stated.
link
0cf8612b2e1e 813 days ago
If I were willing to drop $4k on that setup, I might as well get the real NVidia offering.

The hobbyist market needs something priced well under $1k to make it accessible.

link