AWS r8g.metal-24xlvsAWS r8g.xlarge

r8g.metal-24xl pairs 96 vCPUs with 768GB of RAM at $5.6554/hr On-Demand (about $4072/mo at 24×7). r8g.xlarge pairs 4 vCPUs with 32GB at $0.2356/hr (~$170/mo). r8g.xlarge is 96% cheaper per hour than r8g.metal-24xl ($5.4197/hr gap).

Because both instances are in the **r8g family**, the only thing that changes between them is sizing — same silicon, same architecture (AWS Graviton (ARM64)), same burstable/sustained behavior. The choice is purely about how much capacity you actually need: r8g.metal-24xl gives you 96 vCPUs and 768GB of RAM, r8g.xlarge gives you 4 vCPUs and 32GB. AWS scales pricing close to linearly within a family, so picking the right size is mostly about right-sizing your workload, not getting a better deal per vCPU.

On raw price-per-performance, the two are r8g.xlarge delivers ~2299% more single-thread Sysbench score per dollar (590 vs 14157 points per $1/hr). That's the cleanest signal we have for "which one runs your workload faster per dollar," but it only matters if your workload is single-thread-bound; for parallel workloads the multi-core scores (319512 vs 13169) are what to weigh. Spot pricing flips many of these comparisons — when r8g.metal-24xl drops to $1.5269/hr and r8g.xlarge drops to $0.0750/hr, the cheap-per-hour winner can swing meaningfully.

In practice, pick r8g.metal-24xl when your workload is closer to memory-optimized (memory-bound work — in-memory databases, real-time analytics, large caches). Pick r8g.xlarge when it's closer to memory-optimized (memory-bound work — in-memory databases, real-time analytics, large caches). When neither side is obviously right, the cheaper hourly rate usually wins for fault-tolerant batch workloads, while the higher single-core score usually wins for latency-sensitive web traffic. The regional pricing tables linked from each instance page below show where each is currently cheapest — sometimes a >20% regional gap flips the comparison entirely.