>>105796196
>low iq retard didnt get spoonfed once he instantly pissed and shiddded his pants all over while lying in hopes of no one here knowing anything about the llm space at all

>Doesn't matter if it's ollama, LMStudio, llama.cpp, Transformers, etc, they all contribute to each other's stuff.
lmstudio is literally a proprietary binary blob lcpp wrapper that doesnt contribute anything
ollama is also a wrapper for lcpp that basically didnt contribute anything while specifically creating drama by acting as if their team does anything except wait for lcpp to implement something before they can git pull, picrel
transformers is an entire separate project working in a completely different ecosystem than "make llms work on single user pc that will serve only 1 user with consumer hardware" that the rest of the ones mentioned are doing
and the entire reason why ik_lcpp fork exists, a fork with better performance than lcpp for some models, is because of drama

brown npc retard