g7.2xlarge

Analysis

The g7.2xlarge is a gpu instance instance in the g7 series with 8 vCPUs and 32 GiB of memory on Intel Xeon Scalable (Granite Rapids) (up to 3.9 GHz), which makes it balanced at 4 GiB of memory per vCPU.

Compared with the previous generation, it costs 158% more than the g6.2xlarge on AMD EPYC 7R13 ($1,126 more a month per instance), in exchange for the newer processor.

Running it in N. Virginia instead of Frankfurt saves $461 a month per instance: $2.52/hour against $3.15/hour, a 25% 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.

It carries 1 GPU with 32 GB of GPU memory, so most of the price is the accelerator rather than the CPUs. It has local instance storage (1x440 GB NVMe SSD), which is fast but lost when the instance stops. Network: Up to 60 Gigabit.

It is the cheapest of the 2 processor variants AWS sells at this size and generation. The g7e.2xlarge on Intel Xeon Scalable (Emerald Rapids) costs 33% more, and no others also sit above it.

Per vCPU it is one of the dearer gpu instance types: 85% of the 78 current types in the family cost less than its $0.3150 per vCPU-hour. The premium mostly pays for the accelerators. On demand it is $2.52/hour in US East (N. Virginia), or $1,840 for a 730-hour month.