Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Open-weight AI is having its Kubernetes moment. Let's not ruin it. Parent comment
I'm running this stuff at home on my desktop and using it through an app on my phone. 60-140TPS depending on model / use case.
It's more than fast enough to even maintain voice conversation.
There are no comments on this comment yet.
I'm running this stuff at home on my desktop and using it through an app on my phone. 60-140TPS depending on model / use case.
It's more than fast enough to even maintain voice conversation.