G7e instances provide up to 2.3 times faster inference than their G6e predecessors, supporting demanding AI models including large language and multimodal generative models. Equipped with up to eight RTX PRO 6000 GPUs each with 96 GB memory and next-generation Intel Xeon processors, they cater to workloads needing both graphics and AI acceleration.
These instances also support NVIDIA GPUDirect for improved multi-GPU communication and low-latency networking via EFA in UltraClusters. Along with deployment in other US regions, their availability offers customers enhanced computing power for various AI and spatial computing applications.
Source & further reading
Amazon EC2 G7e instances now available in US West (Oregon) region ↗Source published 2026-02-04. This report was prepared with AI assistance from the linked primary-source material. Claims and limitations should be checked against the original announcement or research.