AWS EC2 Instance

g6.16xlarge

The g6.16xlarge is a GPU-accelerated AWS EC2 instance with 64 vCPUs and 256 GB of memory, 1 L4 GPU, powered by AMD. Ideal for deep learning training, high-performance computing, and GPU-intensive inference workloads. On-demand pricing starts at $3.3968/hr in us-east-1.

Price History

Pricing by Region

Region On-Demand Spot Reserved 1Y
us-east-1$3.397$1.398$2.632
us-east-2$3.397$0.970$2.632
us-west-2$3.397$1.294$2.632
eu-north-1$3.603$2.791
ca-central-1$3.772$0.653$2.922
ap-south-1$4.079$3.160
me-central-1$4.171$3.231
ap-northeast-2$4.177$0.660$3.236
eu-central-1$4.248$1.454$3.291
ap-southeast-5$4.279$3.315
eu-west-2$4.312$1.448$3.341
eu-west-3$4.312$1.314$3.341
ap-southeast-2$4.417$1.523$3.422
ap-northeast-1$4.926$3.817
sa-east-1$5.774$4.473

Frequently Asked Questions

What is the g6.16xlarge?
The g6.16xlarge is a GPU-accelerated AWS EC2 instance with 64 vCPUs and 256 GB of memory, 1 L4 GPU, powered by AMD. Ideal for deep learning training, high-performance computing, and GPU-intensive inference workloads. On-demand pricing starts at $3.3968/hr in us-east-1.
What is the cheapest region for g6.16xlarge?
us-east-1 at $3.397/hr on-demand.
How much does g6.16xlarge cost per month?
Starting at $2479.66/mo on-demand in us-east-1, or $476.84/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.