---
title: "AWS Unveils Trainium3 UltraServer, Teases More Powerful Trainium4 With Nvidia Support"
type: "News"
locale: "en"
url: "https://longbridge.com/en/news/268318799.md"
description: "At AWS re:Invent 2025, Amazon Web Services introduced the Trainium3 UltraServer, featuring the new Trainium3 AI chip with enhanced performance and energy efficiency. The system supports up to a million chips, significantly increasing capacity. AWS also announced the upcoming Trainium4 chip, which will integrate Nvidia's NVLink Fusion, enhancing compatibility with Nvidia GPUs. This development aims to attract developers working with Nvidia's CUDA ecosystem."
datetime: "2025-12-02T22:21:36.000Z"
locales:
  - [zh-CN](https://longbridge.com/zh-CN/news/268318799.md)
  - [en](https://longbridge.com/en/news/268318799.md)
  - [zh-HK](https://longbridge.com/zh-HK/news/268318799.md)
---

> Supported Languages: [简体中文](https://longbridge.com/zh-CN/news/268318799.md) | [繁體中文](https://longbridge.com/zh-HK/news/268318799.md)


# AWS Unveils Trainium3 UltraServer, Teases More Powerful Trainium4 With Nvidia Support

Add  as your preferred news source on Google

 Add Now

At AWS re:Invent 2025, Amazon Web Services unveiled its newest AI training chip, the Trainium3, along with a powerful new machine called the Trainium3 UltraServer.

This system is built on AWS's advanced 3-nanometer Trainium3 chip and their own networking tech, which reportedly offers over four times the performance and memory of the last generation.

Each UltraServer can hold 144 chips, and AWS claims that you can connect thousands of these servers, allowing for up to a million Trainium3 chips to work together—ten times the previous capacity.

They also pointed out a significant energy efficiency improvement of around 40%, which is crucial as the demand for power in global data centers keeps rising.

Some customers, like Anthropic, Karakuri, SplashMusic, and Decart, are already using the Trainium3 to lower their inference costs. Additionally, AWS teased its next chip, the Trainium4, which is currently in the works.

This new chip will utilize Nvidia's NVLink Fusion interconnect, allowing Trainium4 systems to work alongside Nvidia GPUs while preserving Amazon's cost-effective server design.

This could make AWS a more appealing choice for developers looking to create AI models that fit into Nvidia's CUDA ecosystem.

For comments and feedback contact: editorial@rttnews.com

Business News

### Related Stocks

- [Amazon.com, Inc. (AMZN.US)](https://longbridge.com/en/quote/AMZN.US.md)
- [Direxion Daily AMZN Bull 2X Shares (AMZU.US)](https://longbridge.com/en/quote/AMZU.US.md)

## Related News & Research

- [AWS introducing a new UK customer addendum](https://longbridge.com/en/news/281226104.md)
- [Jump on the Dip or Get Out Now? Jefferies Weighs in on Amazon Stock (AMZN)](https://longbridge.com/en/news/280945727.md)
- [Why Nvidia stock may rebound after recent losses](https://longbridge.com/en/news/281411634.md)
- [Reply signs strategic cooperation deal with AWS to accelerate cloud and AI adoption](https://longbridge.com/en/news/281486685.md)
- [Bureau Veritas To Offer AI Assessment To European Enterprises In Partnership With AWS](https://longbridge.com/en/news/281397262.md)