alt Hacker News6 Mac Studios for 100k USD. Consider it a rule of thumb now - 100k to run 1T params, scales linearly.
Replies
root_axis • yesterday at 7:55 PM
If you have 100k you can just buy a few b200s.
6 Mac Studios for 100k USD. Consider it a rule of thumb now - 100k to run 1T params, scales linearly.
If you have 100k you can just buy a few b200s.
Out of curiosity, what do you do to distribute the weights and inference across the multiple machines?