Nemotron 3 Ultra: Open Moe Hybrid Mamba-Transformer for Agentic Reasoning [pdf] research.nvidia.com 22 points by victormustar 11 hours ago
2001zhaozhao 6 hours 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)?
throwa356262 9 hours 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.
This model seems like a really big deal. Is this the biggest Western open-source AI model in the world (beating out Llama3 405B)?
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.