Nemotron 3 Super
Nemotron 3 Super is a fully open 120B-parameter (12B active) hybrid Mamba-Transformer MoE model that delivers unmatched compute efficiency, 1M-token context for long-term memory, and top-tier accuracy for multi-agent reasoning in software development, cybersecurity, and complex workflows.
Available for Chat, Vision, and File Uploads.
Performance Benchmarks
How do you want to interact?
Start a Conversation
Ask anything.
Have a natural conversation, brainstorm ideas, draft emails, or ask for advice.
Use a Persona
Specialized Experts.
Instruct the AI to act as a Coding Tutor, Marketing Expert, or Travel Guide.
Why use Nemotron 3 Super?
High Compute Efficiency
The hybrid Mamba-transformer MoE architecture delivers 50% higher token generation throughput compared to other open models, with up to 2.2× higher inference throughput than comparable alternatives
Multi-Agent Optimization
Designed to run many collaborating agents on a single GPU with 120B total parameters but only 12B activated per forward pass, optimized for reasoning, tool calling, and instruction following
Extended Context Window
Supports a 1 million token context length that enables persistent long-term memory for agents across complex, extended task sequences, eliminating goal drift
Capability Examples
How to use
Go to Chat
Navigate to the "AI Chat" page.
Select Model
Ensure Nemotron 3 Super is selected.
Type Prompt
Ask a question or paste code.
Interact
Refine the answer by replying to the AI.
Compare LLMs Side-by-Side
Is Nemotron 3 Super better than Claude 3.5 or Gemini? Test same prompts simultaneously in the Chat Playground.
Open Chat PlaygroundMade with ❤ by AI4Chat