one would hope model weights are already high entropy enough and would not be improved by a general-purpose memory compression algo?

It turns out that there is still lots of room for improvement: https://huggingface.co/prism-ml/Ternary-Bonsai-2-27B-gguf

We brute force AI models right now because a) we don’t know better, and b) it’s premature optimization.

I beg to differ on point b, but no one is delaying their next model just so they can concentrate on optimization.

It’s coming though.

One example: https://siliconangle.com/2026/07/28/ai-model-compression-sta...

Another is separating the the intelligence part of the model from the known facts part of the model (which can be better compressed)

The Chinese breakthroughs are often around optimization. And I gather it's because they are constrained and very bright so it's a natural progression.

IMO Restrictions are exactly what sparks creativity in people... whereas too many options leads to choice paralysis, which is what I fear is a big problem in the FOSS world.

Don't get me wrong... I think having choices is still good, I just think that having too many choices is not equally as good, or necessarily better.

Compression doesn't really work for model weights.

Model quantization and model distillation are two techniques to reduce model size.

It was sarcastic