AN LLM RUNNING ON A BUSINESS CARD IN YOUR POCKET two years ago running a local model meant a screaming laptop fan and one token per second of garbage output today a raspberry pi runs a chatbot and a macbook air matches gpt-3.5 and a used rtx 3090 gets you close to gpt-4 for
LLM running on a business card in your pocket
A Raspberry Pi can run a chatbot, matching GPT-3.5.