Bookmarked and will come back to this. One thing that may be if interest to add is for AMD cards with 20gb of ram. I’d suppose that it would be Qwen 2.5 34B with maybe less strict quant or something.

Also, it may be interesting to look at the AllenAI molmo related models. I’m kind of planning to do this myself but haven’t had time as yet.

That’s a good point, I don’t remember much ghosting on those. I guess it might depend on the phosphor used. If it was tuned to only fluoresce for that imperceptible off time and no longer it would probably work.

I guess it’s a similar idea to quantum dots, but if those quantum dots fluoresced for just a bit longer.

I think this would result in some pretty intense ghosting and other undesirable artifacts.