r9gd.48xlarge

Analysis

The r9gd.48xlarge is a memory optimized instance in the r9gd series with 192 vCPUs and 1536 GiB of memory on AWS Graviton5 (up to 3.3 GHz), which makes it memory-heavy at 8 GiB of memory per vCPU.

Within the same generation and size, the r9g.48xlarge on AWS Graviton5 costs $12.33/hour, 20% less ($2,226 a month).

Running it in N. Virginia instead of Frankfurt saves $2,262 a month per instance: $15.38/hour against $18.48/hour, a 20% spread. It is not offered in Canada Central, São Paulo, Ireland, London, Mumbai, Singapore, Sydney and Tokyo, so plan around that if you need a presence there.

Compared with the previous generation, it costs 9.0% more than the r8gd.48xlarge on AWS Graviton4 ($926 more a month per instance), in exchange for the newer processor.

It has local instance storage (3 x 3800 GB NVMe SSD), which is fast but lost when the instance stops. Network: 100 Gigabit.

On demand it costs $15.38/hour in US East (N. Virginia), $11,225 a month if left running, which puts it mid-table for memory optimized types at the 52nd percentile per vCPU ($0.0801 per vCPU-hour) and the 68th percentile per GiB ($0.0100 per GiB-hour).

Looking beyond its own line, 8 of 20 current types with 192 vCPUs and similar memory are cheaper. The cheapest of those is the r6a.48xlarge on AMD EPYC 7R13 at $10.89/hour.