Yeah, agree, but that's the point, really. If I could buy a 16Tb machine with 4 TPUs for ~$5K and run a frontier model locally, I would.

I'm in Australia, so we're probably not getting access to Fable again. We're learning that a faster model + better harness/framework > smarter model. So being able to run GLM5.2 locally and super-fast would be great.