The Llama derivatives suck. The small and medium Qwen 2.5 derivatives do too. They have very little information compressed in them and they are very unreliable.

As far as I can tell, the big SaaS models also suck and have done so for quite a long time by now. They do some autocomplete stuff and destroy people's minds.

I'll give this business that it can do machine translation cheaply, but it's not good and likely never will be.