Hugging Face has been fielding M&A interest for your local LLM

Genuine question : is there something that they are claiming about ~%15 word prediction accuracy? Most of the time when a local model feels dumb its not the quant, its the chat template. a lot of what's discussed in the article naturally. Most of the time when a local model feels dumb its not the quant, its the chat template. a lot of sense to me.