What gpu are you running models on?
What gpu are you running models on?


I have used the micro variant primarily with perplexica and I must say it is really good for summation and for answering further questions, especially when it comes to these tasks in my testing it has outclassed instruct models that are 2-3 times its size.
But still no one is willing to move to another platform. I have talked to many of my friends about moving to a more secure platform for messaging or social media, but nobody is willing to move because everyone they know is on a platform developed by meta. And I think they are right, it is impossible to make everyone individually switch, we need new rules and regulations being put in place in order to at least protect some parts of the lives of us and everyone around us.