r7a.48xlarge by Amazon Web Services
(All-cores)
(Single-core)
Specifications #
Server Metadata #
Vendor ID | aws |
Name | r7a.48xlarge |
Description | Memory optimized [AMD processors] Gen7 48xlarge |
Family | Memory Optimized |
Series | r7a |
Hw Virt | |
Status | active |
Observed At | 2026-11-17T03:21:45.163129 |
Availability #
| Region / ID | Spot | Ondemand |
|---|---|---|
Northern Virgina (US) / us-east-1 | 3.18288 USD/h | 14.6064 USD/h |
Oregon (US) / us-west-2 | 4.38275 USD/h | 14.6064 USD/h |
Ohio (US) / us-east-2 | 4.620867 USD/h | 14.6064 USD/h |
Hyderabad (IN) / ap-south-2 | 7.5968 USD/h | 15.0701 USD/h |
Stockholm (SE) / eu-north-1 | 1.604033 USD/h | 15.5328 USD/h |
Aragón (ES) / eu-south-2 | 3.083933 USD/h | 16.345 USD/h |
Dublin (IE) / eu-west-1 | 5.448833 USD/h | 16.345 USD/h |
Tokyo (JP) / ap-northeast-1 | 6.343633 USD/h | 17.6198 USD/h |
Frankfurt (DE) / eu-central-1 | 6.255133 USD/h | 17.6198 USD/h |
Processor #
vCPUs | 192 |
Hypervisor | nitro |
CPU Allocation | Dedicated |
CPU Cores | 192 |
CPU Speed | 3.7 GHz |
CPU Architecture | x86_64 |
CPU Manufacturer | AMD |
CPU Family | EPYC |
CPU Model | 9R14 |
CPU L1D Cache | 32 KiB |
CPU L1D Cache Total | 6 MiB |
CPU L1I Cache | 32 KiB |
CPU L1I Cache Total | 6 MiB |
CPU L2 Cache | 1 MiB |
CPU L2 Cache Total | 192 MiB |
CPU L3 Cache | 32 MiB |
CPU L3 Cache Total | 768 MiB |
CPU Flags | fpu, vme, de, pse, tsc, msr, pae, mce, cx8, apic, sep, mtrr, pge, mca, cmov, pat, pse36, clflush, mmx, fxsr, sse, sse2, ht, syscall, nx, mmxext, fxsr_opt, pdpe1gb, rdtscp, lm, constant_tsc, rep_good, nopl, nonstop_tsc, cpuid, extd_apicid, aperfmperf, tsc_known_freq, pni, pclmulqdq, monitor, ssse3, fma, cx16, pcid, sse4_1, sse4_2, x2apic, movbe, popcnt, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, cmp_legacy, cr8_legacy, abm, sse4a, misalignsse, 3dnowprefetch, topoext, perfctr_core, ssbd, perfmon_v2, ibrs, ibpb, stibp, ibrs_enhanced, vmmcall, fsgsbase, bmi1, avx2, smep, bmi2, invpcid, avx512f, avx512dq, rdseed, adx, smap, avx512ifma, clflushopt, clwb, avx512cd, sha_ni, avx512bw, avx512vl, xsaveopt, xsavec, xgetbv1, xsaves, avx512_bf16, clzero, xsaveerptr, rdpru, wbnoinvd, arat, avx512vbmi, pku, ospke, avx512_vbmi2, gfni, vaes, vpclmulqdq, avx512_vnni, avx512_bitalg, avx512_vpopcntdq, rdpid, flush_l1d |
Ecpus | 191.5 |
Scalability | 99.74 |
System Resources and Accelerators #
| Memory | |
|---|---|
Memory Amount | 2 TB |
Memory Amount Actual | 2 TB |
Memory Generation | DDR5 |
Memory Speed | 4800 Mhz |
| Accelerators | |
|---|---|
Accelerator Count | 0 |
Accelerator Memory Min | 0 MiB |
Accelerator Memory Total | 0 MiB |
Accelerators |
| Storage | |
|---|---|
Storage Size | 0 GB |
Storages | |
Compatible Storage IDs | standard, gp2, gp3, st1, sc1, io1, io2 |
| Network | |
|---|---|
Network Speed Baseline | 50 Gbps |
Network Speed Max | 50 Gbps |
Network Storage Speed Baseline | 40 Gbps |
Network Storage Speed Max | 40 Gbps |
Inbound Traffic | 0 GB/month |
Outbound Traffic | 0 GB/month |
IPv4 | 0 |
CPU and System Topology #
Server Description #
High-density memory-optimized cloud server featuring 192 dedicated AMD EPYC cores, DDR5 memory bandwidth, and 50 Gbps baseline networking.
Amazon Web Services r7a.48xlarge is a memory-optimized instance built on x86_64 architecture and powered by the AWS Nitro hypervisor. It features 192 dedicated physical AMD EPYC 9R14 processor cores running at 3.7 GHz and 1536 GB of DDR5 RAM, delivering an 8:1 memory-to-core ratio with 652.3 GB/sec uncached memory read bandwidth. The instance provides 50 Gbps baseline network bandwidth and includes AVX-512 instruction set extensions. Benchmark results highlight top-tier performance in multi-core processing, static web serving throughput, software compilation, and in-memory key-value operations such as Redis SET performance reaching 323 million operations per second. However, it lacks attached local storage, relying on external network storage, and exhibits lower token generation rates during CPU-based LLM inference compared to GPU-accelerated architectures. The high memory density and dedicated core allocation provide qualitative cost efficiency for resource-demanding enterprise applications, large-scale in-memory databases, and compute-intensive compilation workloads.
Economics #
Performance #
Memory Bandwidth#
Compression #
OpenSSL #
Geekbench Single-Core #
Geekbench Multi-Core #
Passmark CPU Scores #
| BENCHMARK | SCORE |
|---|---|
Mark | 143,337 |
Compression | 3,918,828 |
Encryption | 240,079 |
Extended Instructions | 299,673 |
Floating Point Maths | 998,855 |
Integer Maths | 1,156,847 |
Physics | 38,387 |
Prime Numbers | 3,049 |
Single Threaded | 2,887 |
String Sorting | 563,665 |
Passmark Memory Scores #
| BENCHMARK | SCORE |
|---|---|
Memory Mark | 2,849 |
Database Operations | 31,580 |
Memory Latency | 78 |
Memory Read Cached | 27,825 |
Memory Read Uncached | 27,018 |
Memory Write | 25,417 |
Stress-ng Raw Scores #
Stress-ng Relative Multicore Performance #
Static Web Server#
Redis#
Alternatives #
Servers of the Same Family #
| INSTANCE | vCPUs | MEMORY | Accelerators |
|---|---|---|---|
| r7a.medium | 1 | 8 GiB | 0 |
| r7a.large | 2 | 16 GiB | 0 |
| r7a.xlarge | 4 | 32 GiB | 0 |
| r7a.2xlarge | 8 | 64 GiB | 0 |
| r7a.4xlarge | 16 | 128 GiB | 0 |
| r7a.8xlarge | 32 | 256 GiB | 0 |
| r7a.12xlarge | 48 | 384 GiB | 0 |
Similar Servers #
| INSTANCE | VENDOR | vCPUs | MEMORY | Accelerators |
|---|