/AI1h ago

NVIDIA releases Nemotron-3-Ultra, a 558B-parameter LatentMoE-Mamba-2 hybrid model featuring a 1M context length

It scores 89% on LiveCodeBench and 86.8% on MMLU-Pro

--0--
Sentiment
Sentiment building, check back later.
Cluster Engagement
-
Views
-
Comments
-
Reposts
-
Bookmarks
Expand data
Posts from X
Most Activity
Most ActivityTimeline
VIEWS7.1KBOOKMARKS4LIKES91REPLIES7
Hugging Face@huggingface

Nemotron 3 Ultra!

1hViews 7.1KLikes 91Bookmarks 4
RETWEETS1
Hugging Face@huggingface

Nemotron 3 Ultra!

1hViews 7.1KLikes 91Bookmarks 4