Executive Summary
Amazon Web Services (AWS) has announced the general availability of its new Amazon EC2 G7 instances, becoming the first major cloud provider to offer NVIDIA's RTX PRO 4500 Blackwell Server Edition GPUs. These instances, powered by custom Intel Xeon Scalable processors, are engineered for high-performance AI inference, graphics, and data analytics workloads. The G7 family offers significant performance improvements over the previous G6 generation, featuring enhanced GPU memory, faster networking, and advanced video processing capabilities.
Key Takeaways
* Core Technology: G7 instances are accelerated by NVIDIA RTX PRO 4500 Blackwell Server Edition GPUs, each with 32 GB of memory, 5th Gen Tensor Cores, and 4th Gen RT Cores.
* Performance Gains: Delivers up to 4.6x better AI inference performance and up to 2.1x higher graphics performance compared to previous-generation G6 instances.
* Networking and Storage: Features up to 700 Gbps of EFA-enabled network bandwidth (a 7x increase over G6) and supports up to 7.6 TB of local NVMe SSD storage.
* Configuration Options: Available in 7 sizes, scaling up to 8 GPUs (256 GB total GPU memory), 192 vCPUs, and 768 GiB of system memory.
* Target Audience: Designed for users with demanding GPU workloads, including AI inference, graphics rendering, video transcoding, virtual desktop infrastructure (VDI), and data analytics.
* Availability: G7 instances are available immediately in the US East (Ohio) and US West (Oregon) AWS regions, with pricing available via On-Demand, Savings Plans, and Spot Instances.
Strategic Importance
This launch reinforces AWS's leadership in high-performance computing by providing customers with first-mover access to NVIDIA's latest Blackwell GPU architecture, aiming to capture a larger share of the rapidly growing AI inference and professional graphics markets.