Nemotron 3 Ultra

Open MoE model for long-running agents

agentsadvancedFree tier

Overview

NVIDIA’s Nemotron 3 Ultra is an open Mixture-of-Experts hybrid Mamba-Transformer described as suited for long-running agents. It ships with open weights, training data, and recipes, and is notable for its long context and throughput improvements, which matter for developers deploying agentic inference pipelines.

Best For

+ml-engineers
+infra-engineers
+researchers

News & Updates

LangChain Deep Agents tuned for NVIDIA Nemotron 3 Ultra deliver 10x throughput boost

NVIDIA Nemotron 3 Ultra is offering leading performance at lower cost than top closed models with the largest and most widely adopted AI agent orchestration platform. LangChain tuned its Deep Agents harness for NVIDIA Nemotron 3 Ultra, achieving the highest accuracy among open models, while completing more tasks at higher throughput and running at 10x […]

new_tools7/22/2026

Loading AI Digest

Overview

Best For

News & Updates

LangChain Deep Agents tuned for NVIDIA Nemotron 3 Ultra deliver 10x throughput boost