←back to thread

I Self-Hosted Llama 3.2 with Coolify on My Home Server

(geek.sg)
221 points whitefables | 1 comments | 16 Oct 24 05:26 UTC | HN request time: 0.372s | source
Show context
keriati1 ◴[16 Oct 24 07:29 UTC] No.41856491[source]▶
What model size is used here? How much memory does the GPU have?
replies(1): >>41857104 #
1. thawab ◴[16 Oct 24 09:18 UTC] No.41857104[source]▶
he is using the 3b one, since it's the default when downloading it from ollama: https://ollama.com/library/llama3.2