alt Hacker Newsprobably; 32-64 is the range where local models get extraordinarily useful, and in my experience any sub-4 quants get ridiculously incoherent, which is why those models tend to try to 'wow' people with tok/s rather than benchmarks.
haven't tried it yet though.
Qwen3.8-Flash-Next fits in 80GB on strix halo. That's when I started real "vibe" coding with them. Speed is still an issue if I want to move fast and break things, but I've built a little universe for development (I assume many people have also) and it's cruising.
But yeah, 32-64 is the gateway I think. If Qwen4 can make a leap in the flast-next MoE and hit 64 GB on VRAM w/context, that's definitely the cloud killer to me.