![Deploy AI Workloads at Scale with Bottlerocket and NVIDIA-Powered Amazon EC2 Instances | NVIDIA Technical Blog Deploy AI Workloads at Scale with Bottlerocket and NVIDIA-Powered Amazon EC2 Instances | NVIDIA Technical Blog](https://developer-blogs.nvidia.com/wp-content/uploads/2022/02/image2.png)
Deploy AI Workloads at Scale with Bottlerocket and NVIDIA-Powered Amazon EC2 Instances | NVIDIA Technical Blog
Shashank Prasanna on Twitter: "You want the best perf/cost, single-GPU instance for training/inference: g5.xlarge Based on latest Ampere architecture, NVIDIA A10G GPU has 24GB memory. This option is for the most of
![GPU-Accelerated Amazon Web Services | Boost Performance and Scale Deep Learning and HPC Applications. GPU-Accelerated Amazon Web Services | Boost Performance and Scale Deep Learning and HPC Applications.](https://www.nvidia.com/content/dam/en-zz/Solutions/Data-Center/gpu-cloud-computing/amazon-data-center-gpu-cloud-social-media.jpg)
GPU-Accelerated Amazon Web Services | Boost Performance and Scale Deep Learning and HPC Applications.
![Price-Performance Analysis of Amazon EC2 GPU Instance Types using NVIDIA's GPU optimized seismic code | AWS HPC Blog Price-Performance Analysis of Amazon EC2 GPU Instance Types using NVIDIA's GPU optimized seismic code | AWS HPC Blog](https://d2908q01vomqb2.cloudfront.net/e6c3dd630428fd54834172b8fd2735fed9416da4/2021/08/09/nvidia-esdk-fig1.png)