The c5d.24xlarge pairs 96 vCPU with 192 GiB of RAM, the 2.00 GiB-per-vCPU ratio that marks a compute-optimized instance. In the name, "c" stands for compute, "5" is the generation, "d" marks local NVMe storage and "24xlarge" is the size within the c5d family. It runs on Intel Xeon Platinum 8275L at 3.4 GHz, and AWS introduced it in November 2019. AWS has since shipped c6i, c7i, c8i and c9g; c6i.24xlarge is the direct replacement at this size, scoring 1,618,546 CoreMark/s against this instance's 1,546,080 — roughly 5% more throughput for the same vCPU count. Spot's node ladder tops out below this size, so c5d.24xlarge becomes 6 × ch.vs1.2xlarge (96 vCPU, 192 GiB combined), about 95% 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.
Match qualityScale-out match
c5d.24xlarge gives you 96 vCPU and 192 GiB in a single machine. The largest comparable Spot node, ch.vs1.2xlarge, is 16 vCPU and 32 GiB, so the equivalent here is 6 nodes rather than one.
Spot runs as managed Kubernetes, so a 6-node pool is the normal way to run things rather than a workaround. If your workload already sits behind a load balancer, a queue or a scheduler, it spreads across them without changes. If it needs all 96 cores and 192 GiB in one process, it does not.
No local diskc5d.24xlarge comes with 4 × 900 GB NVMe SSD attached to the machine. Spot nodes use network storage only, so that disk doesn't come with it. If you were using it as fast scratch space, you'd move to a persistent volume or object storage, which are slower to read.
