NvidiaReleased on Apr 7, 2025

Llama 3.1 Nemotron Ultra 253B v1: Benchmarks, Pricing & Context Window

Llama 3.1 Nemotron Ultra 253B v1 is a language model from Nvidia, released in April 2025.

A 253B parameter derivative of Meta Llama 3.1 405B Instruct, developed by NVIDIA using Neural Architecture Search (NAS) and vertical compression. It underwent multi-phase post-training (SFT for Math, Code, Reasoning, Chat, Tool Calling; RL

Llama 3.1 Nemotron Ultra 253B v1 API

API access coming soon

Llama 3.1 Nemotron Ultra 253B v1 will be available through our gateway shortly.

Llama 3.1 Nemotron Ultra 253B v1 examples

Recent arena outputs from Llama 3.1 Nemotron Ultra 253B v1, picked from the highest-ranked matchups.

Llama 3.1 Nemotron Ultra 253B v1 license

Llama 3.1 Nemotron Ultra 253B v1 is released under the Llama 3.1 Community License license, which restricts commercial use, has 253.0B parameters, has a knowledge cutoff of December 2023.

License
Llama 3.1 Community License
Non-commercial
Parameters
253.0B
Knowledge cutoff
December 2023

FAQ

Common questions about Llama 3.1 Nemotron Ultra 253B v1.

What is the Llama 3.1 Nemotron Ultra 253B v1 release date?

Llama 3.1 Nemotron Ultra 253B v1 was released on April 7, 2025 by Nvidia.

Who created Llama 3.1 Nemotron Ultra 253B v1?

Llama 3.1 Nemotron Ultra 253B v1 was created by Nvidia.

How many parameters does Llama 3.1 Nemotron Ultra 253B v1 have?

Llama 3.1 Nemotron Ultra 253B v1 has 253.0 billion parameters.

What is the license for Llama 3.1 Nemotron Ultra 253B v1?

Llama 3.1 Nemotron Ultra 253B v1 is released under the Llama 3.1 Community License license. This is an open-source/open-weight license.

What is the knowledge cutoff date for Llama 3.1 Nemotron Ultra 253B v1?

Llama 3.1 Nemotron Ultra 253B v1 has a knowledge cutoff of December 2023. This means the model was trained on data up to this date and may not have information about events after this time.