BTW, as I wrote that post, Qwen 32B coder came out.

Now a single 3090 can beat GPT-4o, and do it way faster! In coding, specifically.

Yep.

32B fits on a “consumer” 3090, and I use it every day.

72B will fit neatly on 2025 APUs, though we may have an even better update by then.

I’ve been using local llms for a while, but Qwen 2.5, specifically 32B and up, really feels like an inflection point to me.