I noticed there didn’t seem to be a community about large language models, akin to r/localllama. So maybe this will be it.

For the uninitiated, you can easily try a bleeding edge LLM in your browser here.

If you loved that, some places to get started with local installs and execution are here-

https://github.com/ggerganov/llama.cpp

https://github.com/oobabooga/text-generation-webui

https://github.com/LostRuins/koboldcpp

https://github.com/turboderp/exllama

and for models in general, the renowned TheBloke provides the best and fastest releases-

https://huggingface.co/TheBloke