g5.48xlarge

Analysis

The g5.48xlarge is a gpu instance instance in the g5 series with 192 vCPUs and 768 GiB of memory on AMD EPYC 7R32 (up to 2.8 GHz), which makes it balanced at 4 GiB of memory per vCPU.

Running it in N. Virginia instead of São Paulo saves $8,321 a month per instance: $16.29/hour against $27.69/hour, a 70% spread. It is not offered in Singapore, so plan around that if you need a presence there.

The newer g6.48xlarge on AMD EPYC 7R13 is 18% cheaper at $13.35/hour, which makes the g5.48xlarge hard to justify for new deployments.

It carries 8 GPUs with 192 GB of GPU memory, so most of the price is the accelerator rather than the CPUs. It has local instance storage (2 x 3800 GB NVMe SSD), which is fast but lost when the instance stops. Network: 100 Gigabit.

It is the largest of the 8 g5 sizes. Dropping to the g5.24xlarge saves $5,945 a month. Unit price is not flat across the series ($0.0640 to $0.2515 per vCPU-hour), so the size changes the rate you pay.

On demand it costs $16.29/hour in US East (N. Virginia), $11,890 a month if left running, which puts it mid-table for gpu instance types at the 36th percentile per vCPU ($0.0848 per vCPU-hour) and the 47th percentile per GiB ($0.0212 per GiB-hour).