(cerebras.ai)

426 points benchmarkist | 2 comments | 19 Nov 24 00:15 UTC | HN request time: 0.416s | source

1. gdiamos ◴[19 Nov 24 03:25 UTC] No.42179843[source]▶

I'm so curious to see some multi-agent systems running with inference this fast.

replies(1): >>42179877 #

2. ipsum2 ◴[19 Nov 24 03:31 UTC] No.42179877[source]▶

There's no good open source agent models at the moment unfortunately.

Llama 3.1 405B now runs at 969 tokens/s on Cerebras Inference