Llama3 on Groq

by matanyallon 4/19/2024, 7:04 PMwith 7 comments

by Orason 4/19/2024, 7:10 PM

That's impressive. I asked to summarise an article in 5 bullet points, and the output was 812.81 T/s on Llama 3 8B.

by frozenporton 4/20/2024, 1:48 AM

LLama3 looks particularly good at tool calling

Groq's low latency is particularly good for tool calling

Seems like two techs that will make coding obsolete :-)

by Alifatiskon 4/20/2024, 10:13 AM

Is the python lib open-source? I could only find the ja lib for Groq.

by WhatsNameon 4/19/2024, 8:55 PM

What is tbe cost per Mio. Token for llama3 70b on groq?

by jacooperon 4/19/2024, 9:06 PM

When is Mixtral 8x22b coming?