The c8gn.12xlarge is a compute-optimized AWS EC2 instance: 48 vCPU and 96 GiB of memory, 2.00 GiB per vCPU. In the name, "c" stands for compute, "8" is the generation, "gn" marks AWS Graviton (ARM) processors and enhanced networking and "12xlarge" is the size within the c8gn family. It runs on AWS Graviton4 Processor at 2.8 GHz, and AWS introduced it in June 2025. AWS has since shipped c9g; c9g.12xlarge is the direct replacement at this size, scoring 1,639,344 CoreMark/s against this instance's 1,393,020 — roughly 18% more throughput for the same vCPU count. No single Spot node covers 48 vCPU and 96 GiB, so the equivalent is a fleet: 3 × ch.vs1.2xlarge, 48 vCPU and 96 GiB in total, $2.84/hr on AWS in US East (N. Virginia), from $0.123/hr on Rackspace Spot. 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 | $2.844 | $0.643 | $0.123 | $2.721 savings | ||
| US Central, Chicago | no AWS region | $0.033 | ||||
| US Central, Dallas | no AWS region | $0.333 | ||||
| Hong Kong | $3.766 | $0.123 | $3.643 savings | |||
| Sydney, Australia | $3.713 | $1.385 | $0.123 | $3.590 savings | ||
| London, UK | $3.371 | $0.585 | $0.393 | $2.978 savings | ||
| US West, San Jose | $3.555 | $0.529 | $0.006 | $3.549 savings | ||
| US Central, Dallas 2 | no AWS region | $0.366 | ||||
| US East, N. Virginia 2 | $2.844 | $0.643 | $0.486 | $2.358 savings |