A 34yo Recreational Programmer rants about the future of local LLMs and the shift from local computing to cloud.Let's talk about it.🔗 Relevant Links› Origin...
I can run a 32B model on my 6GB GPU with old DDR4 32GB ram… this cant work without destorying the computer industry.
Open source AI tuned to one task is were the industry is headed frontier models are kinda a dead end tech wise people just havent figured it out yet beacuse we are still in the bubble.
I can run a 32B model on my 6GB GPU with old DDR4 32GB ram… this cant work without destorying the computer industry.
Open source AI tuned to one task is were the industry is headed frontier models are kinda a dead end tech wise people just havent figured it out yet beacuse we are still in the bubble.