Content pfp
Content
@
https://opensea.io/collection/dev-21
0 reply
0 recast
2 reactions

Nik The Savage🎩🥷 pfp
Nik The Savage🎩🥷
@nikthesavage
groq is working perfect rn, set the model to "llama3 70B " Its performance is close to gpt4 and super fast. https://groq.com/
1 reply
1 recast
8 reactions

eggman 🔵 pfp
eggman 🔵
@eggman.eth
..that is really unfortunate naming. I didn't even see the "q", I just assumed X's Grok. Which is barely worth 4GB of VRAM, let alone its titanic MoE size. llama3 70b is genuinely frightening. I thought the 400b model might rival an early gpt4, but 70b is already on its heels. Absolutely insane lift from meta tbh
1 reply
0 recast
0 reaction