AWS Launches Its Biggest Instance Yet, With Over 4TB RAM

The Big One is here! AWS has leaped far ahead from competitors, in officially unveiling its largest EC2 virtual machine yet, one with over 4TB of memory. Yes, 4TB.

This, while Microsoft Azure taps out at 2TB, while Google doesn’t go beyond 416GB.

Amazon Web Services had already promised that it was working on instance types that offered anywhere between 4TB to 16TB of memory to users. And it has started to fulfill its promise by launching its largest virtual machine in terms of memory size.

The x1e.32xlarge instance, catchy name and all, offers a whopping 4.19TB of RAM, decimating the previous largest VM that only offered 2TB of memory.

As you may expect, these instances are for specialized applications that need these large memory capacities. Only a few of them are in existence — the SAP HANA in-memory database and its various tools, for example, which these gigantic instances are certified to run.

In fact, these are the users that AWS is targeting with these massive virtual boxes, and SAP will offer direct support for running these applications on these instances.

AWS cloud evangelist Jeff Barr:

“Many of our customers are already running production SAP applications on the existing x1.32xlarge instances. With today’s launch, these customers can now store and process far larger data sets, making them a great fit for larger production deployments.”

Each instance runs on quad-socket Intel Xeon E7 8880 processors, along with a pair of 1,920GB SSDs. They also support 14Gbps networking capacity to EBS storage, and 25Gbps links to other instances, as long as they are running within a single placement group.

Goes to say that these are the most expensive AWS machines yet, with on-demand pricing in the US East region is set at an eye-watering $26.688 per hour, and in Tokyo, this figure goes up to $38.688.

Amazon Web Services says that these instances can be bought on demand or reserved through the AWS Marketplace, Management Console, CLI, or by using its SDKs.

They are available in the US East (northern Virginia), US West (Oregon), Asia Pacific (Tokyo) and EU (Ireland) regions.