g6e.8xlarge

Analysis

The g6e.8xlarge is a gpu instance instance in the g6e series with 32 vCPUs and 256 GiB of memory on AMD EPYC 7R13 (up to 2.6 GHz), which makes it memory-heavy at 8 GiB of memory per vCPU.

Within the same generation and size, the g6.8xlarge on AMD EPYC 7R13 costs $2.01/hour, 56% less ($1,835 a month).

Running it in N. Virginia instead of Tokyo saves $1,489 a month per instance: $4.53/hour against $6.57/hour, a 45% spread. It is not offered in Canada Central, São Paulo, Ireland, London, Singapore and Sydney, so plan around that if you need a presence there.

It carries 1 GPU with 48 GB of GPU memory, so most of the price is the accelerator rather than the CPUs. It has local instance storage (1 x 900 GB NVMe SSD), which is fast but lost when the instance stops. Network: 25 Gigabit.

The newer g7e.8xlarge on Intel Xeon Scalable (Emerald Rapids) is 16% dearer at $5.27/hour.

It is size 4 of 8 in the g6e series. Stepping up to the g6e.12xlarge gives 48 vCPUs and 384 GiB for $4,354 more a month. Dropping to the g6e.4xlarge saves $1,113 a month. Unit price is not flat across the series ($0.1184 to $0.4652 per vCPU-hour), so the size changes the rate you pay.