Nemotron 3 Ultra: Open Moe Hybrid Mamba-Transformer for Agentic Reasoning [pdf] (research.nvidia.com) 23 points by victormustar 3mo ago ↗ HN
[–] throwa356262 3mo ago ↗ Is this the one from Jensens Computex presentation the other day?It is significantly bigger than Qwen for the same level of intelligence, but I think the key strength was inference speed.
[–] 2001zhaozhao 3mo ago ↗ This model seems like a really big deal. Is this the biggest Western open-source AI model in the world (beating out Llama3 405B)?
2 comments
[ 2.6 ms ] story [ 16.7 ms ] threadIt is significantly bigger than Qwen for the same level of intelligence, but I think the key strength was inference speed.