Awesome model
#1
by Tom9000 - opened
Really fine work here.
I've only been testing it now for about an hour or so, but loving it already. Not encountered any issues (pulled and recompiled latest llama.cpp), nothing broken, nothing weird, everything smooth like a butter, both text generation and vision. So far at least.
With this one and 'qwen3.5 27b heretic' - I think I got all I ever needed. We've peaked. Can stop now all further development, no need any more.
Release the RAM!
Thanks! As I said in another place... this model is really something. I actually felt a tiny, fleeting sting from something it said... first time that's ever happened. Heh, you know it's good when it can even ruffle your feathers.