Rhaedas

Most models are going to require CUDA. There are some AMD ones out there, but it's a totally different math and setup. As for the one I mentioned, it's a pretty new idea so there are only a few out there, maybe just one (Qwen based). But I did get a 31B model to work on my 12GB, I just had to move from Ollama to llama.cpp to gain the control needed to set the parameters, and fine tune what it put on the CUDA to the max it would take. I had Claude help me along the way.

It's new enough that there aren't any good abliterated/uncensored models yet.

16GB is plenty for even older model setups. Now they've got a few models designed so you load just parts of the model onto the GPU (Mixture of Experts) and use the CPU for less referenced sections, so you get both reasonable speed and a much more complex model.

The fact that they backed down on it means it's not a hard fact, but something they want you to believe. Or maybe they're going back to the drawboard to optimize it better. Or realistically, it does take that much to run well, but they'd rather deal with the aftermath than say it out loud since it's less people shouting.

If they could make a better Windows, they would. But it's possible it's built on top of so much crap that they'd have to start from the beginning, and probably would just do like they did from the start, use someone else's software to branch off of.

Not a manual that came with the game, but back when SimCity 2000 first came out, there was a companion book in bookstores for it. Lots of hints and backstories on development, if I remember. Lots of humor too. It was a great read.