AWS m5d.xlargevsAWS m5dn.large

m5d.xlarge pairs 4 vCPUs with 16GB of RAM at $0.2260/hr On-Demand (about $163/mo at 24×7). m5dn.large pairs 2 vCPUs with 8GB at $0.1360/hr (~$98/mo). m5dn.large is 40% cheaper per hour than m5d.xlarge ($0.0900/hr gap).

Both are generation-5 general-purpose instances, but they run on different silicon: **m5d.xlarge** is Intel Xeon (x86_64), **m5dn.large** is Intel Xeon (x86_64). AMD variants (suffix `a`) are typically 10% cheaper than Intel siblings at comparable single-thread performance. Graviton variants (suffix `g`) are usually 20–40% cheaper but require ARM64-compatible binaries — most modern Linux stacks are fine, but verify any compiled extensions, native modules, or third-party binaries before migrating. Same vCPU/RAM ratio, same network performance class, different processor.

On raw price-per-performance, the two are m5dn.large delivers ~57% more single-thread Sysbench score per dollar (4823 vs 7551 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 (3286 vs 1555) are what to weigh. Spot pricing flips many of these comparisons — when m5d.xlarge drops to $0.1069/hr and m5dn.large drops to $0.0489/hr, the cheap-per-hour winner can swing meaningfully.

In practice, pick m5d.xlarge when your workload is closer to general-purpose (balanced general-purpose workloads with a 1:4 vCPU-to-memory ratio). Pick m5dn.large when it's closer to general-purpose (balanced general-purpose workloads with a 1:4 vCPU-to-memory ratio). 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.