@DeFi_Hanzo I have 2 questions, which model are you using currently and how turboquant is helping you out. As turboquant is related to kv cache, if i have 16 gb ram, bigger models can not get loaded, currently I am using lm studio and jackrong 9b model.
i am having skill issue while using vercel, i am unable to deploy latest version of commit. i am deleting the project and reimporting the same again. it's just a POC that i am currently working on