The m8g.metal-48xl is a general-purpose AWS EC2 instance: 192 vCPU and 768 GiB of memory, 4.00 GiB per vCPU. In the name, "m" is the general-purpose line, "8" is the generation, "g" marks AWS Graviton (ARM) processors and "metal-48xl" is the size within the m8g family. It runs on AWS Graviton4 Processor at 2.7 GHz, and AWS introduced it in September 2024. AWS has since shipped m9g; m9g.metal-48xl is the direct replacement at this size, scoring 5,972,006 CoreMark/s against this instance's 4,450,626 — roughly 34% more throughput for the same vCPU count. No single Spot node covers 192 vCPU and 768 GiB, so the equivalent is a fleet: 12 × gp.vs2.2xlarge, 192 vCPU and 768 GiB in total, about 94% below the US East (N. Virginia) on-demand rate. Spot delivers compute as managed Kubernetes, so a node pool of that size is the native shape of the answer rather than a workaround — provided the workload scales horizontally.
| Region | AWS on-demand | AWS Spot | 1-yr Reserved | 3-yr Reserved | Rackspace Spot | You save |
|---|---|---|---|---|---|---|
| US East, N. Virginia | $8.617 | $2.471 | $5.700 | $3.909 | $0.492 | $8.125 savings |
| US Central, Chicago | no AWS region | $0.492 | ||||
| US Central, Dallas | no AWS region | $0.612 | ||||
| Hong Kong | $11.848 | $7.838 | $5.374 | $0.132 | $11.716 savings | |
| Sydney, Australia | $10.771 | $1.077 | $7.125 | $4.885 | $1.932 | $8.839 savings |
| London, UK | $9.965 | $0.997 | $6.581 | $4.531 | $2.652 | $7.313 savings |
| US West, San Jose | $10.053 | $1.005 | $6.630 | $4.581 | $1.812 | $8.241 savings |
| US Central, Dallas 2 | no AWS region | $0.012 | ||||
| US East, N. Virginia 2 | $8.617 | $2.471 | $5.700 | $3.909 | $1.812 | $6.805 savings |