Nvidia debuts Nemotron 3 with hybrid MoE and Mamba-Transformer to drive efficient agentic AI

Published: 1 day ago (December 15, 2025 at 12:00 AM EST)

1 min read

Source: VentureBeat

Nvidia Announces Nemotron 3

Nvidia launched the new version of its frontier models, Nemotron 3, by leaning in on a model architecture that the world’s most valuable company said offers more accuracy and reliability for agents. Nemotron 3 will be available in three sizes: Nemotron 3 Nano with 30 B parameters, mainly for targete…

Back to Blog

AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders

Introduction AdaSPEC is a new method that speeds up large language models by using a small draft model for the initial generation pass, followed by verificatio...

As AI Grows More Complex, Model Builders Rely on NVIDIA

Unveiling what it describes as the most capable model series yet for professional knowledge work, OpenAI launched GPT‑5.2 today. The model was trained and deplo...

How the Google AI Agents Intensive Transformed My Understanding of Agentic AI

Introduction When I joined the Google & Kaggle AI Agents Intensive program, I had only a basic idea of what AI agents really were. I assumed they were similar...

NVIDIA Partners With Mistral AI to Accelerate New Family of Open Models

Announcement Today, Mistral AI announcedhttps://mistral.ai/news/mistral-3 the Mistral 3 family of open‑source multilingual, multimodal models, optimized acro...

Nvidia Announces Nemotron 3

Related posts

AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders

As AI Grows More Complex, Model Builders Rely on NVIDIA

How the Google AI Agents Intensive Transformed My Understanding of Agentic AI

NVIDIA Partners With Mistral AI to Accelerate New Family of Open Models

Nvidia Announces Nemotron 3