It features 55 billion active parameters and multi-token prediction.
During the past 6 months, Nemotron has grown from 24 to 48 on the AAI, and we're just getting started.
NVIDIA Nemotron 3 Ultra is now live!
Frontier accuracy, 5X greater speed, 30% lower cost.
Deploy however you need - on-premise, on the cloud, or at the edge.
Model is live on HuggingFace under the OpenMDW 1.1 license.
https://www.youtube.com/watch?v=D8LIIvQVGS4
Today we're shipping Nemotron 3 Ultra.
A 550B MoE frontier-intelligence open model built for long-running agents.
It delivers 5x faster inference and lowers the cost of complex agentic tasks by up to 30% versus other open frontier models.
It features 55 billion active parameters and multi-token prediction.
During the past 6 months, Nemotron has grown from 24 to 48 on the AAI, and we're just getting started.
NVIDIA Nemotron 3 Ultra is now live!
Frontier accuracy, 5X greater speed, 30% lower cost.
Deploy however you need - on-premise, on the cloud, or at the edge.
Model is live on HuggingFace under the OpenMDW 1.1 license.
https://www.youtube.com/watch?v=D8LIIvQVGS4
Positive users hail NVIDIA's Nemotron 3 Ultra 550B MoE open model as an exciting advance for fast agent workflows, while negative users dismiss it as a ploy to sell expensive GPUs and demand more accessible hardware.
