Amazon introduced the new Trainium3 chip; Faster artificial intelligence training

Amazon Last night, during the AWS re:Invent 2025 event, a new generation of proprietary chips for artificial intelligence processing named Trainium3 introduced that it is supposed to Training speed of models to increase significantly.

According to Amazon, the Trainium3 chip offers four times better performance and four times more memory than its predecessor. This improvement makes progress both in the field of training and derivation of artificial intelligence models.

Optimum energy consumption is also one of the main axes of the new generation. According to Amazon, Trainium3 systems About 40 percent They consume less energy and at the same time provide more computing power. Given the rapid growth of data centers and increasing energy demand, AWS says the new design can reduce infrastructure strain and lower operational costs associated with AI processing.

Amazon also has a huge system called Trainium3 UltraServer It has revealed that it uses 3nm Trainium3 chips. Each UltraServer includes 144 Trainium3 chips, and customers can connect thousands of these systems together.

At the largest possible scale, a single server unit can One million Trainium3 chips to use; A figure that shows a tenfold improvement compared to the previous generation.

Amazon’s first Trainium3 chip customers

Several companies have already started using Trainium3. AnthropicJapanese startup Karakuriservice SplashMusic and company Descartes Among the customers are those who, according to Amazon, have achieved better performance in inference and other advantages by benefiting from this new chip.

The company also confirmed that it has started development of its next-generation proprietary processor, Trainium4. The most important change mentioned for the next generation is support for NVIDIA NVLink Fusion which enables the construction of massive and integrated artificial intelligence processing clusters.

This choice shows that Amazon no longer intends to use its chips as a complete replacement for processors Nvidia to introduce, but rather to build a hybrid ecosystem where AWS’s proprietary chip can work alongside and even complement Nvidia’s GPUs.