g7e.4xlarge

Analysis

The g7e.4xlarge is a gpu instance instance in the g7e series with 16 vCPUs and 128 GiB of memory on Intel Xeon Scalable (Emerald Rapids) (up to 3.2 GHz), which makes it memory-heavy at 8 GiB of memory per vCPU.

Compared with the previous generation, it costs 33% more than the g6e.4xlarge on AMD EPYC 7R13 ($726 more a month per instance), in exchange for the newer processor.

Within the same generation and size, the g7.4xlarge on Intel Xeon Scalable (Granite Rapids) costs $3.04/hour, 24% less ($698 a month).

Running it in N. Virginia instead of London saves $2,154 a month per instance: $4.00/hour against $6.95/hour, a 74% spread. It is not offered in Canada Central, São Paulo, Ireland, Singapore and Sydney, so plan around that if you need a presence there.

It carries 1 GPU with 96 GB of GPU memory, so most of the price is the accelerator rather than the CPUs. It has local instance storage (1 x 1900 GB NVMe SSD), which is fast but lost when the instance stops. Network: 50 Gigabit.

It is size 2 of 6 in the g7e series. Stepping up to the g7e.8xlarge gives 32 vCPUs and 256 GiB for $927 more a month. Dropping to the g7e.2xlarge saves $464 a month. Unit price is not flat across the series ($0.1646 to $0.4204 per vCPU-hour), so the size changes the rate you pay.