π“Ÿ host1.bitchan.one

𓀐 @8pvoNyay

⏱ 6h seenβ›“ 0πŸ‘ 0β§– 1

filter [-]

languages:onother

Nta https://github.com/ggml-org/llama.cpp Fun fact. It was originally created because the head maintainer wanted to run LLMs on his MacBook, and now Apple Silicon is one of the best platforms to run local models on from a price to performance and convenience perspective.⏱ 52m↩