[tcsenpai]

I think they should start aiming for 20B models along with 32B and 7B. Usually 7B is enough for a 8GB GPU, 32B requires a 24GB GPU for decent quants (I can fit a 32B with IQ3_XXS but is not ideal) while 20-ish B models (such as magistral or gpt-oss) are a perfect fit for 16GB GPUs

[embedding-shape]

Depends heavily on the architecture too, I think a free-for-all to find the better sizes is still kind of ongoing, and rightly so. GPT-OSS-120B for example fits in around 61GB VRAM for me when on MXFP4.

Personally, I hope GPU makers instead start adding more VRAM, or if one can dream, expandable VRAM.

[refulgentis]

Unlikely to see more VRAM in the short term, memory prices are thru the roof :/ like, not subtly, 2-4x.