←back to thread

Llama.cpp 30B runs with only 6GB of RAM now

(github.com)
1311 points msoad | 1 comments | 31 Mar 23 20:37 UTC | HN request time: 0.247s | source
Show context
yodsanklai ◴[31 Mar 23 22:48 UTC] No.35394809[source]▶
Total noob questions.

1. How does this compare with ChatGPT3

2. Does it mean we could eventually run a system such as ChatGPT3 on a computer

3. Could LLM eventually replace Google (in the sense that answers could be correct 99.9% of the time) or is the tech inherently flawed

replies(4): >>35394861 #>>35394958 #>>35395176 #>>35396372 #
1. addisonl ◴[31 Mar 23 22:53 UTC] No.35394861[source]▶
Minor correction, chatGPT uses GPT-3.5 and (most recently, if you pay $20/month) GPT-4. Their branding definitely needs some work haha. We are in track for you to be able to run something like chatGPT locally!