Seconding this. If you know how to build with a dumber model it scales crazy well. And Qwen 3.8 Flash Next is just wildly good even at low quants. I'm trying to find it's limits and I've been using it for over a week building and haven't hit a wall yet.
Really? I hit a wall immediately, though I'm using it to implement things originally written in a proof language, and wasn't that good at prompting to begin with.
Are you using it for coding? I'm looking for a good coding model to use for Xcode and NextJS apps