NVIDIA Nemotron Developer Repository

Open and efficient models for agentic AI. Training recipes, deployment guides, and use-case examples for the Nemotron family.

Why Nemotron?

Repository Overview

nemotron/
│
├── src/nemotron/recipes/    Training recipes (complete, reproducible pipelines)
│
├── usage-cookbook/          Usage cookbooks (deployment and model usage guides)
│
└── use-case-examples/       Examples of leveraging Nemotron in agentic workflows

Which section should I use?

What is Nemotron?

NVIDIA Nemotron is a family of open, high-efficiency multimodal models purpose-built for agentic AI.

Model Tiers:

• Nano — Optimized for edge and PC deployments
• Super — Single GPU deployment with highest throughput
• Ultra — Multi-GPU datacenter applications

Nemotron models excel at coding, math, scientific reasoning, tool calling, instruction following, and visual reasoning. Deploy across edge, single GPU, or data center environments with support for NeMo, TensorRT-LLM, vLLM, SGLang, and NIM microservices.

Training Recipes

The Nemotron respository provides reproducible training pipelines from raw data to deployment-ready models. These implementations reflect how large language models are actually trained: careful experimentation, validation gates, and systematic optimization.

Why Complete Pipelines?

Training a production model involves interconnected components. Isolated examples miss how stages interact. Complete pipelines show:

• How data quality affects downstream performance across pretraining, SFT, and RL
• Which training techniques actually work together, not just in theory
• Where validation gates prevent failures and maintain reproducibility
• How to balance competing objectives across stages

Because these are complete systems, you can extract specific techniques with confidence. Each component has been proven to work in context.

Each Recipe Includes

• 🎨 Synthetic Data Generation - Scripts to generate synthetic datasets using NVIDIA-NeMo/DataDesigner
• 🗂️ Data Curation - Scripts to prepare training data using NVIDIA NeMo Curator for scalable data processing, filtering, and quality enhancement
• 🔁 Training - Complete training loops with hyperparameters using:
• NVIDIA-NeMo/Megatron-Bridge for Megatron models
• NVIDIA-NeMo/Automodel for HuggingFace models
• NVIDIA-NeMo/NeMo-RL when RL is needed
• Includes GPU-accelerated last-mile data processing (tokenization + optional sequence packing) for optimal training efficiency
• 📊 Evaluation - Benchmark evaluation on standard suites using NVIDIA NeMo Evaluator
• 📖 Documentation - Detailed explanations of each stage

Available Recipes

Nemotron 3 Super

A complete training recipe for the frontier Hybrid Mamba Latent Mixture-of-Experts Transformer model with state-of-the-art reasoning, coding, and agentic capabilities.

Open-Source Data Only: These recipes train exclusively on the open-sourced subset of training data. Results will differ from the tech report benchmarks, which used additional proprietary data. Use these recipes as reference implementations to apply the methodology with your own data.

Model Specifications:
- 120B total / 12B active parameters
- Multi-stage RL pipeline: 3× RLVR + 2× SWE-RL + RLHF across 21 reward environments
- Asynchronous GRPO with decoupled training and inference

What You Can Extract:
- Large-scale pretraining with data curriculum
- Multi-domain SFT pipeline
- Multi-environment RLVR with 21 simultaneous reward environments
- SWE-RL with container-isolated sandbox execution
- GenRM-based RLHF with principle-following rewards
- Asynchronous GRPO at 1K GPU scale

Resources:
- Training Guide
- Tech Report
- Model Weights (Instruct)

Nemotron 3 Nano

A complete training recipe for the open, efficient Mixture-of-Experts hybrid Mamba-Transformer model optimized for agentic reasoning.

Open-Source Data Only: These recipes train exclusively on the open-sourced subset of training data. Results will differ from the tech report benchmarks, which used additional proprietary data. Use these recipes as reference implementations to apply the methodology with your own data.

Model Specifications:
- 31.6B total parameters, 3.6B active per forward pass
- 25 trillion pretraining tokens with curriculum learning
- Up to 1M context length
- 3.3x higher inference throughput than similarly sized models

What You Can Extract:
- Curriculum-based pretraining with two-phase data mixture
- Long-context extension via CPT methodology
- Multi-domain SFT with 12+ data sources
- InfinityByte cross-domain code synthesis
- Tool-calling fine-tuning and budget-controlled reasoning
- Multi-environment RLVR with GRPO
- GenRM reward modeling with circular comparison
- DPO for tool hallucination reduction

Resources:
- Training Guide
- Tech Report
- Model Weights (Base)
- Model Weights (Instruct)
- Model Weights (FP8)

Usage Cookbooks

Practical deployment and model usage guides for Nemotron models.

Use Case Examples

End-to-end examples demonstrating practical applications in the use-case-examples/ directory:

• Agentic Workflows — Multi-step AI agents with planning, context management, and external tools
• RAG Systems — Pipelines combining retrieval with Nemotron models for grounded outputs
• Tool Integration — Structured tool calling, function execution, and data enrichment
• Production Patterns — Scalability, monitoring, and deployment architectures

Nemotron Open Datasets

More than just weights, recipes, and libraries: Nemotron is committed to opening data across many domains, training phases, and use cases.

💡 Feature Requests & Ideas

Have an idea for improving Nemotron models? Create a Discussion topic for it!

If you have a feature request, feel free to open an Issue and tag it as enhancement.

Your feedback helps shape the future of Nemotron models!

Documentation

• Nemotron 3 Super Training Guide – frontier model training recipe
• Nemotron 3 Nano Training Guide – efficient model training recipe
• NeMo-Run Configuration – execution profiles and job orchestration
• Data Preparation – data preparation module
• Contributing Guidelines – how to contribute
• Changelog – version history

Contributing

We welcome contributions: examples, recipes, or other tools. Please read the Contributing Guidelines before submitting pull requests.

Security

To report any vulnerabilities, please reach out to security@nvidia.com

License

Apache 2.0 License — see LICENSE for details.

NVIDIA Nemotron — Open and efficient models for agentic AI.