g6.4xlarge

Analysis

The g6.4xlarge is a gpu instance instance in the g6 series with 16 vCPUs and 64 GiB of memory on AMD EPYC 7R13 (up to 2.6 GHz), which makes it balanced at 4 GiB of memory per vCPU.

Within the same generation and size, the g6f.4xlarge on AMD EPYC 7R13 costs $0.9500/hour, 28% less ($272 a month). The other variants are the g6e.4xlarge at $3.00.

It is 19% cheaper than the older g5.4xlarge on AMD EPYC 7R32, so staying on the previous generation costs more as well as being slower. The newer g7.4xlarge on Intel Xeon Scalable (Granite Rapids) is 130% dearer at $3.04/hour.

Running it in N. Virginia instead of São Paulo saves $676 a month per instance: $1.32/hour against $2.25/hour, a 70% spread. It is not offered in Ireland and Singapore, so plan around that if you need a presence there.

It carries 1 GPU with 24 GB of GPU memory, so most of the price is the accelerator rather than the CPUs. It has local instance storage (1 x 600 GB NVMe SSD), which is fast but lost when the instance stops. Network: Up to 25 Gigabit.

It is size 3 of 8 in the g6 series. Stepping up to the g6.8xlarge gives 32 vCPUs and 128 GiB for $505 more a month. Dropping to the g6.2xlarge saves $252 a month. Unit price is not flat across the series ($0.0531 to $0.2012 per vCPU-hour), so the size changes the rate you pay.