

I made sure to have it set to download new chapters regardless.
Admittedly I didn’t try that hard to get things running smoothly since the whole web ui was sluggish for me. I just ponied up for more RAM though so that might help if I decide to give it another go.
Last night I managed to run Qwen Flash Next iq2 XS using Strata in docker on a VM
I passed through my 3090, 64GB of DDR4, 12 vcores of my 5960x,
Managed 90t/s
I’ll probably try a larger version soon but QFN already seems a lot more capable than 3.6 35b A3B, and runs better than Qwen 3.8 dense in llama.cpp