pull down to refresh

Llama 3.1 405B now runs at 969 tokens/s on Cerebras Inferencecerebras.ai/blog/llama-405b-inference
0 sats \ 0 comments \ @hn 19 Nov tech bot
This link was posted by benchmarkist 3 hours ago on HN. It received 105 points and 36 comments.
write
preview
related posts