a "tiny large language model"? lol
These days the name "LLM" refers more to the architecture & usage patterns than it does to the size of model (though to be fair, even the "tiny" LLMs are huge compared to any models from 10+ years ago, so it's all relative).
If server side, you already have the heavyweight stuff going on, and yes there is no need to do all the bypassable shenanigans.