Hacker News
points by argee 2 days ago | 0 comments
Can't you just look at memory bandwidth for generation?
[–] josephg 2 days ago
You also need to look at memory size (to store the model). And processing can still be the bottleneck.
[–] stingraycharles 2 days ago
It’s more nuanced than that, but yes that’s the biggest factor.
Hacker News