Run NVIDIA Nemotron 3 Nano as a fully managed serverless model on Amazon Bedrock
Machine Learning Blog
This article announces NVIDIA Nemotron 3 Nano's availability as a fully managed serverless model on Amazon Bedrock.
- Hybrid Mixture-of-Experts architecture with 30B parameters, only 3B active
- Leads benchmarks in coding, reasoning, math, and tool calling tasks
- 256K context length supports long-range sequence modeling efficiently
- Accessible via AWS CLI, SDKs, and OpenAI-compatible API
- Integrates with Amazon Bedrock Guardrails for content safety filtering
- Works with Amazon Knowledge Bases for RAG workflows
- Available across eight AWS regions globally
Nemotron 3 Nano enables efficient agentic AI applications for finance, cybersecurity, software development, and retail use cases without infrastructure management.
The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.
The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.