Mistral-Nemotron Overview

Description:

Mistral-Nemotron is a large language model produced by Mistral and optimised by NVIDIA that generates human-like text and can be used for a variety of natural language processing tasks, such as text generation, language translation, and text summarization. It is also suitable for Agentic workflows due to its tool calling capabilities.

This model is ready for commercial usage.

Third-Party Community Consideration

This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party’s requirements for this application and use case; more information available on the model here (scroll past animation).

License/Terms of Use:

Access to this model is governed by the NVIDIA API Trial Terms of Service.

To deploy and customize Mistral models with NIMs in your environment, please contact Mistral AI to acquire necessary licenses at https://mistral.ai/license-mistral-models-for-nvidia-inference-microservices.

Use of this model is subject to compliance with all applicable laws, and users are responsible for ensuring such compliance."

Deployment Geography:

Global

Use Case:

Researchers and developers in the field of natural language processing (NLP) and artificial intelligence (AI) may use the Mistral-Nemotron model for tasks such as language translation, text summarization, and conversational AI applications.

Release Date:

Release Date on Build.NVIDIA.com:
06/11/2025, https://build.nvidia.com/mistralai/mistral-nemotron

Model Architecture:

• Architecture Type:
  • Transformer
• Network Architecture:
  • Modified Transformer

Input:

• Input Type(s):
  • Text
• Input Format(s):
  • String
• Input Parameters:
  • One-Dimensional (1D)
• Other Properties Related to Input:
  • 128K Maximum Context Length

Output:

• Output Type:
  • Text
• Output Format:
  • String
• Output Parameters:
  • One-Dimensional (1D)
• Other Properties Related to Output:
  • Maximum Context Length 128K

Software Integration:
Runtime Engine(s):
['TensorRT-LLM', 'vLLM']

Supported Hardware Microarchitecture Compatibility:
['NVIDIA Hopper']

[Preferred/Supported] Operating System(s):
['Linux']

Model Version(s):
{'v1'}

Training, Testing, and Evaluation Datasets:

Benchmark Score:

Coding & Programming

Instruction Following

Mathematics

General Knowledge & Reasoning

MMLU by Language

Data Collection Method by dataset

• Hybrid: Automated, Human, Synthetic

Labeling Method by dataset

• Hybrid: Automated, Human, Synthetic

Inference:

• Engine:
  • TensorRT-LLM, vLLM

Test Hardware :

• H100

Ethical Considerations:
NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.

Please report security vulnerabilities or NVIDIA AI Concerns here