nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 is a 30 billion parameter large language model developed by NVIDIA, featuring a hybrid Mixture-of-Experts (MoE) architecture with Mamba-2 and Attention layers. Designed for both reasoning and non-reasoning tasks, it can generate intermediate reasoning traces for higher accuracy on complex prompts. The model supports English, German, Spanish, French, Italian, and Japanese, and is optimized for agent systems, chatbots, and RAG applications.
Loading preview...
Model Overview
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16 is a 30 billion parameter large language model (LLM) developed by NVIDIA, featuring a unique hybrid Mixture-of-Experts (MoE) architecture. It combines 23 Mamba-2 and MoE layers with 6 Attention layers, utilizing 3.5 billion active parameters. This model is specifically designed to excel in both reasoning and non-reasoning tasks, offering a configurable option to generate intermediate reasoning traces for improved accuracy on challenging prompts.
Key Capabilities
- Advanced Reasoning: Can generate detailed reasoning traces before providing a final answer, enhancing solution quality for complex problems.
- Hybrid MoE Architecture: Leverages a combination of Mamba-2 and Attention layers for efficient processing.
- Multilingual Support: Supports English, German, Spanish, French, Italian, and Japanese.
- Extensive Training: Pre-trained on 25 trillion tokens, including a significant amount of synthetic data across various domains like code, math, science, and general knowledge.
- Long Context: Supports a maximum input and output size of 1 million tokens.
Good For
- AI Agent Systems: Ideal for developers building sophisticated AI agents that require robust reasoning capabilities.
- Chatbots and RAG Systems: Suitable for creating highly accurate and context-aware conversational AI and retrieval-augmented generation applications.
- Instruction Following: Performs well on general instruction-following tasks.
- Commercial Use: Licensed for commercial deployment.