Container
NVIDIA
Llama-3.1-Nemotron-Ultra-253B-v1This container houses the Llama-3.1-Nemotron-Ultra-253B-v1, a reasoning model offering a great tradeoff between accuracy and efficiency. Post-trained for chat, RAG, and tool calling, it supports a 128K context and fits on a single 8xH100 node.
Subscription required to access this content
Join or Subscribe to get accessSubscribe to the product below to access this premium content:
Get Access
Subscribe NowNote: You can gain access to hundreds more GPU-optimized artifacts by creating a free NGC account.

NVIDIA Developer ProgramJoin the Developer Program for access to free tools, support, and tech resources.

NVIDIA AI EnterpriseAccelerate your AI agent development
Already Subscribed?Log in