G7 instances deliver up to 4.6 times better AI inference performance compared to G6, thanks to up to 8 NVIDIA RTX PRO 4500 GPUs and enhanced network bandwidth. They target AI workloads such as conversational assistants, content generation, and recommendation engines requiring low latency and high throughput.
Built on custom Intel Xeon processors with enhanced FP16 performance and Elastic Fabric Adapter support, G7 instances are accessible for SageMaker Studio notebooks in selected AWS US regions. This addition facilitates more efficient AI inference, graphics, and data analytics workflows.
Source & further reading
Amazon SageMaker Studio notebooks now support G7 instance types ↗Source published 2026-08-03. 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.