News for hackers. Stuff that matters.
Re:NVIDIA Nemotron 3 Super by tosh on Thursday March 12, 2026 @07:18AM (#47349118)
a bit less capable but ~comparable to qwen 3.5 122b

~ 2x faster inference than qwen 3.5 122b

~ 7x faster inference than gpt-oss 120b

probably most important: training datasets and training recipe available (!)

in other words this is an open source llm release (not just open weights!)

[ Parent | on HN ]
Re:NVIDIA Nemotron 3 Super by IamTC on Thursday March 12, 2026 @07:25AM (#47349166)
Oh. That's nice. Thanks for sharing this in the comments.
[ Parent | on HN ]