Content
@
https://warpcast.com/~/channel/theai
0 reply
0 recast
0 reaction
Giuliano Giacaglia 🌲
@giu
Llama 3 70B on Groq is: ~17x lower input cost 🤯 ~38x lower output cost 🤯🤯 14x faster @ ~280 vs ~20 tokens per sec 🤯🤯🤯 Compared to OpenAI GPT 4
4 replies
3 recasts
80 reactions
Hardy Yu
@hardzyu17
wow so nice👌
0 reply
0 recast
0 reaction
