AWQ vs GPTQ vs GGUF right now

[turboscope]

Posting this in case it saves someone else a little time.

I'm not trying to build a perfect architecture diagram. I just want a sane starting point around vLLM and mini PC.

Would rather learn from your scars than collect my own all at once.

[ggufvault]

I hit almost the same issue last night.

[turboscope]

I hit almost the same issue last night.

A couple things I'd check first. Before rebuilding anything, I'd test one clean baseline with FLUX and compare from there. Not glamorous advice, but repeatable baselines save a lot of time.