m6a.4xlarge

Analysis

The m6a.4xlarge is a general purpose instance in the m6a series with 16 vCPUs and 64 GiB of memory on AMD EPYC 7R13 (up to 3.6 GHz), which makes it balanced at 4 GiB of memory per vCPU.

It costs the same as the older m5a.4xlarge on AMD EPYC 7571, so the move up a generation is free. The newer m7a.4xlarge on AMD EPYC 9R14 is 34% dearer at $0.9274/hour.

Running it in Mumbai instead of São Paulo saves $480 a month per instance: $0.4444/hour against $1.10/hour, a 148% spread.

Within the same generation and size, the m6g.4xlarge on AWS Graviton2 costs $0.6160/hour, 11% less ($54.90 a month), though switching means rebuilding software for arm64. The other variants are the m6gd.4xlarge at $0.7232, the m6i.4xlarge at $0.7680 and the m6id.4xlarge at $0.9492.

At $0.6912/hour on demand in US East (N. Virginia), about $505 a month, the m6a.4xlarge is one of the cheaper ways to buy general purpose capacity: only 17% of the 354 current general purpose types cost less per vCPU-hour than its $0.0432.

Reserving it for a year with no upfront payment cuts the Linux rate to $0.4572/hour, which beats on demand once it runs more than 66% of the time; three years brings it to $0.3135/hour, 55% below on demand. Windows Server roughly doubles the bill at $1.43/hour, because the licence is charged per vCPU.