

Oh yeah, 16 GB of VRAM is a strange spot to be in. Most of the focus goes onto the models that fit in 24 GB cards.
Qwen 3.6 35b-a3b is pretty solid when you don’t have enough VRAM for a dense model. Most of the weights can be left in RAM and it still runs really quickly.







I feel you on the license thing. There’s the appeal of software that can’t be easily corporatized and then there’s the idea that if I could just get lucky with my own project, I wouldn’t have to work for some soulless company generating value for shareholders.