I’ve got my stuff rigged to hit mixtral-8x7, and dolphin locally, and 3.5-turbo, and the 4-series preview all with easy comparison in emacs and stuff, and in fairness the 4.5-preview is starting to show some edge on 8x7 that had been a toss-up even two weeks ago. I’m still on the mistral-medium waiting list. Until I realized Perplexity will give you a decent amount of Mistral Medium for free through their partnership…
I might not know half of the references like "sama" or "TheBloke", but I could understand the context of them all. Like:
"the lag between some new edge and TheBloke having it quantized for a Mac Mini or 4070 Super,"
Not sure who TheBloke is, but he obviously means "between some new (cutting) edge AI model, and some person scaling it to run on smaller computers with less memory".
Similarly, not sure who Perplexity is, but "Until I realized Perplexity will give you a decent amount of Mistral Medium for free through their partnership" basically spells out that they're a service provider of some kind, that they have partnered with Mistral AI, and you get to use the Mistral Medium model through opening a free account on Perplexity.
I mean, duh!