I agree that as of today, the difference is massive. It's more of a general phlosophical musingon my end, I wonder if the industry tries to go beyond the transformers or earnestly looks at their relative efficiency. I fear it's conceptually easier to spend that VC money on data centers though.

I'm saying this from a mac that has trouble answering large context questions in ollama with a qwen 14b and similar. But the results are good-ish. Go small, I say.

I'm wondering if the end goal should not be to scale down the LLMs to the extend of them running competently on a standard dev laptop and having the inference go there. This way, you still sell a product license (cursor and the likes), model upgrades, but then defer the energy cost on the end user

Fantastique, bienvenue à vous !

La classe ultime, d'une certaine manière. Etre l'exemple que l'on veut donner.