Content pfp
Content
@
0 reply
0 recast
0 reaction

Giuliano Giacaglia pfp
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
94 reactions

Sayonara pfp
Sayonara
@sayo
Haven’t dug much, do they have special hardware or just powerful inference engine?
0 reply
0 recast
0 reaction

Alec James pfp
Alec James
@waj
It’ll be onchain soon, giving smart contracts the power of 70B parameters of computation & intelligence
0 reply
0 recast
0 reaction

ivc pfp
ivc
@ivc
I bet it’s cheaper on runpod
0 reply
0 recast
0 reaction

Yasir Ali pfp
Yasir Ali
@yasirali
Wow
0 reply
0 recast
0 reaction