r8g.2xlarge by Amazon Web Services
(All-cores)
(Single-core)
Specifications
Server Metadata
Vendor ID | aws |
Name | r8g.2xlarge |
Description | Memory optimized [AWS Graviton processors] Gen8 2xlarge |
Family | r8g |
Hw Virt | |
Status | active |
Observed At | 2026-09-13T13:35:18.312054 |
Availability
| REGION / ID | SPOT | ONDEMAND |
|---|---|---|
Hyderabad (IN) / ap-south-2 | 0.066833 USD/h | 0.3303 USD/h |
Mumbai (IN) / ap-south-1 | 0.126133 USD/h | 0.3303 USD/h |
Ohio (US) / us-east-2 | 0.129733 USD/h | 0.4713 USD/h |
Oregon (US) / us-west-2 | 0.22765 USD/h | 0.4713 USD/h |
Northern Virgina (US) / us-east-1 | 0.19298 USD/h | 0.4713 USD/h |
(TH) / ap-southeast-7 | 0.159633 USD/h | 0.4832 USD/h |
(MY) / ap-southeast-5 | 0.156333 USD/h | 0.4832 USD/h |
(MX) / mx-central-1 | 0.153867 USD/h | 0.4948 USD/h |
Stockholm (SE) / eu-north-1 | 0.102633 USD/h | 0.5012 USD/h |
Calgary (CA) / ca-west-1 | 0.116 USD/h | 0.5162 USD/h |
Quebec (CA) / ca-central-1 | 0.1968 USD/h | 0.5162 USD/h |
California (US) / us-west-1 | 0.1721 USD/h | 0.5236 USD/h |
Aragón (ES) / eu-south-2 | 0.0644 USD/h | 0.5271 USD/h |
Dublin (IE) / eu-west-1 | 0.2446 USD/h | 0.5274 USD/h |
Milan (IT) / eu-south-1 | 0.1195 USD/h | 0.5522 USD/h |
London (GB) / eu-west-2 | 0.14075 USD/h | 0.5535 USD/h |
Paris (FR) / eu-west-3 | 0.1848 USD/h | 0.5535 USD/h |
Melbourne (AU) / ap-southeast-4 | 0.094467 USD/h | 0.5648 USD/h |
Sydney (AU) / ap-southeast-2 | 0.1867 USD/h | 0.5648 USD/h |
Jakarta (ID) / ap-southeast-3 | 0.070667 USD/h | 0.5685 USD/h |
Osaka (JP) / ap-northeast-3 | 0.163533 USD/h | 0.5685 USD/h |
Seoul (KR) / ap-northeast-2 | 0.173433 USD/h | 0.5685 USD/h |
Tokyo (JP) / ap-northeast-1 | 0.219567 USD/h | 0.5685 USD/h |
Frankfurt (DE) / eu-central-1 | 0.2248 USD/h | 0.5685 USD/h |
Singapore (SG) / ap-southeast-1 | 0.2361 USD/h | 0.5685 USD/h |
United Arab Emirates / me-central-1 | 0.2375 USD/h | 0.5801 USD/h |
(NZ) / ap-southeast-6 | 0.200033 USD/h | 0.593 USD/h |
Hong Kong (HK) / ap-east-1 | 0.113133 USD/h | 0.6248 USD/h |
Zurich (CH) / eu-central-2 | 0.1119 USD/h | 0.6254 USD/h |
Cape Town (ZA) / af-south-1 | 0.1757 USD/h | 0.6283 USD/h |
Sao Paulo (BR) / sa-east-1 | 0.134633 USD/h | 0.7499 USD/h |
Processor
vCPUs | 8 |
Hypervisor | nitro |
CPU Allocation | Dedicated |
CPU Cores | 8 |
CPU Speed | 2.8 GHz |
CPU Architecture | arm64 |
CPU Manufacturer | AWS |
CPU Model | Neoverse-V2 |
CPU L1D Cache | 64 KiB |
CPU L1D Cache Total | 512 KiB |
CPU L1I Cache | 64 KiB |
CPU L1I Cache Total | 512 KiB |
CPU L2 Cache | 2 MiB |
CPU L2 Cache Total | 16 MiB |
CPU L3 Cache | 36 MiB |
CPU L3 Cache Total | 36 MiB |
CPU Flags | fp, asimd, evtstrm, aes, pmull, sha1, sha2, crc32, atomics, fphp, asimdhp, cpuid, asimdrdm, jscvt, fcma, lrcpc, dcpop, sha3, asimddp, sha512, sve, asimdfhm, dit, uscat, ilrcpc, flagm, ssbs, sb, paca, pacg, dcpodp, sve2, sveaes, svepmull, svebitperm, svesha3, flagm2, frint, svei8mm, svebf16, i8mm, bf16, dgh, rng, bti |
Ecpus | 8 |
Scalability | 100 |
System Resources and Accelerators
| MEMORY | |
|---|---|
Memory Amount | 64 GiB |
Memory Amount Actual | 63 GiB |
| GPU | |
|---|---|
GPU Count | 0 |
GPU Memory Min | 0 MiB |
GPU Memory Total | 0 MiB |
GPUs |
| STORAGE | |
|---|---|
Storage Size | 0 GB |
Storages |
| NETWORK | |
|---|---|
Network Speed Baseline | 3.75 Gbps |
Network Speed Max | 15 Gbps |
Network Storage Speed Baseline | 2.5 Gbps |
Network Storage Speed Max | 10 Gbps |
Inbound Traffic | 0 GB/month |
Outbound Traffic | 0 GB/month |
IPv4 | 0 |
Server Description
An arm64 memory-optimized instance featuring dedicated physical cores and high-bandwidth memory for memory-intensive database and caching workloads.
Amazon Web Services r8g.2xlarge is a memory-optimized instance featuring 8 dedicated arm64 physical cores powered by the AWS Graviton Neoverse-V2 processor at 2.8 GHz. It provides 64.0 GB of RAM, yielding a high memory-to-core ratio of 8.0 GB per core, alongside a 36 MB L3 cache and a 4 Gbps baseline network bandwidth. The instance does not include local storage or GPU hardware. Benchmark results show top-tier memory performance, with Passmark memory scores in the top 10% and large-block read bandwidth in the top 25%. However, cryptographic and LLM inference benchmarks show weaker performance, with encryption and medium-model prompt processing scoring in the bottom 25% and 10% respectively. This profile makes the r8g.2xlarge highly efficient for memory-intensive workloads like caching and in-memory databases, while being less suited for compute-heavy cryptography or AI inference.
Economics
Performance
Memory Bandwidth
Compression
OpenSSL
Geekbench Single-Core
Geekbench Multi-Core
Passmark CPU Scores
| BENCHMARK | SCORE |
|---|---|
Mark | 7699 |
Compression | 53159 |
Encryption | 1510 |
Extended Instructions | 7357 |
Floating Point Maths | 48484 |
Integer Maths | 41722 |
Physics | 2569 |
Prime Numbers | 141 |
Single Threaded | 1944 |
String Sorting | 37135 |
Passmark Memory Scores
| BENCHMARK | SCORE |
|---|---|
Memory Mark | 3231 |
Database Operations | 12134 |
Memory Latency | 47 |
Memory Read Cached | 21194 |
Memory Read Uncached | 20095 |
Memory Write | 21274 |
Stress-ng Raw Scores
Stress-ng Relative Multicore Performance
LLM Inference Speed for Prompt Processing
LLM Inference Speed for Text Generation
Static Web Server
Redis
Alternatives
Servers of the Same Family
| INSTANCE | vCPUs | MEMORY | GPUs |
|---|---|---|---|
| r8g.medium | 1 | 8 GiB | 0 |
| r8g.large | 2 | 16 GiB | 0 |
| r8g.xlarge | 4 | 32 GiB | 0 |
| r8g.4xlarge | 16 | 128 GiB | 0 |
| r8g.8xlarge | 32 | 256 GiB | 0 |
| r8g.12xlarge | 48 | 384 GiB | 0 |
| r8g.16xlarge | 64 | 512 GiB | 0 |
Similar Servers
| INSTANCE | VENDOR | vCPUs | MEMORY | GPUs |
|---|