AWS EC2 Instance

g6.48xlarge

The g6.48xlarge is a GPU-accelerated AWS EC2 instance with 192 vCPUs and 768 GB of memory, 8 L4 GPUs, powered by AMD. Ideal for deep learning training, high-performance computing, and GPU-intensive inference workloads. On-demand pricing starts at $13.3504/hr in us-east-1.

Price History

Pricing by Region

Region On-Demand Spot Reserved 1Y
us-east-1$13.350$8.590$10.343
us-east-2$13.350$3.279$10.343
us-west-2$13.350$5.480$10.343
eu-north-1$14.160$10.970
ca-central-1$14.823$14.823$11.484
ap-south-1$16.031$12.420
me-central-1$16.393$12.700
ap-northeast-2$16.416$1.757$12.718
eu-central-1$16.695$5.432$12.934
ap-southeast-5$16.817$13.029
eu-west-2$16.947$16.947$13.129
eu-west-3$16.947$3.583$13.129
ap-southeast-2$17.358$14.513$13.448
ap-northeast-1$19.362$15.001
sa-east-1$22.693$17.581

Frequently Asked Questions

What is the g6.48xlarge?
The g6.48xlarge is a GPU-accelerated AWS EC2 instance with 192 vCPUs and 768 GB of memory, 8 L4 GPUs, powered by AMD. Ideal for deep learning training, high-performance computing, and GPU-intensive inference workloads. On-demand pricing starts at $13.3504/hr in us-east-1.
What is the cheapest region for g6.48xlarge?
us-east-1 at $13.350/hr on-demand.
How much does g6.48xlarge cost per month?
Starting at $9745.79/mo on-demand in us-east-1, or $1282.39/mo with spot pricing.

Run a free assessment to identify overprovisioned workloads, idle capacity, and your potential savings, in minutes.

Most clusters are overprovisioned.
Let's prove yours is.