Amazon EC2 G7 instances, powered by NVIDIA RTX PRO 4500 Blackwell Server Edition GPUs, are now available in the AWS Europe (Spain) Region. These instances deliver up to 4.6x AI inference performance and 2.1x graphics performance compared to G6 instances. Each instance supports up to 8 GPUs with 32 GB memory per GPU, 192 vCPUs, 700 Gbps EFA networking, 768 GiB system memory, and 7.6 TB NVMe SSD storage. Use cases include AI model deployment, real-time graphics rendering, video transcoding, RAG inference, and real-time data pipelines. G7 instances are available across four AWS regions and can be purchased as On-Demand, Spot, or via Savings Plans.
Questions this post answers
What are the specs of Amazon EC2 G7 instances?
EC2 G7 instances feature up to 8 NVIDIA RTX PRO 4500 Blackwell Server Edition GPUs with 32 GB of memory per GPU, custom Intel Xeon 6 processors, up to 192 vCPUs, 700 Gbps EFA networking bandwidth, 768 GiB of system memory, and up to 7.6 TB of local NVMe SSD storage. They deliver up to 4.6x AI inference performance and 2.1x graphics performance compared to G6 instances. Engineers sizing GPU instances for AI inference workloads track spec comparisons like these on daily.dev.
In which AWS regions are EC2 G7 instances available?
EC2 G7 instances are available in four AWS regions: US East (N. Virginia and Ohio), US West (Oregon), and Europe (Spain). They can be purchased as On-Demand Instances, Spot Instances, or as part of Savings Plans. Teams expanding GPU workloads to European regions find availability updates like this on daily.dev.