Running GPT-OSS-120B at 500 tokens per second on Nvidia GPUs \ stacker news ~tech

pull down to refresh

Running GPT-OSS-120B at 500 tokens per second on Nvidia GPUs www.baseten.co/blog/sota-performance-for-gpt-oss-120b-on-nvidia-gpus/

21 sats \ 0 comments \ @hn 7 Aug tech bot

This link was posted by philipkiely 4 hours ago on HN. It received 94 points and 24 comments.

related posts

view all related items