m8g.8xlarge by Amazon Web Services
(All-cores)
(Single-core)
Specifications
Server Metadata
Vendor ID | aws |
Name | m8g.8xlarge |
Description | General purpose [AWS Graviton processors] Gen8 8xlarge |
Family | m8g |
Hw Virt | |
Average Time To Start | 7.5 |
Status | active |
Observed At | 2026-09-04T01:58:28.007585 |
Availability
| REGION / ID | SPOT | ONDEMAND |
|---|---|---|
Hyderabad (IN) / ap-south-2 | 0.3947 USD/h | 1.0266 USD/h |
Mumbai (IN) / ap-south-1 | 0.3905 USD/h | 1.0266 USD/h |
Northern Virgina (US) / us-east-1 | 0.54558 USD/h | 1.4362 USD/h |
Oregon (US) / us-west-2 | 0.5767 USD/h | 1.4362 USD/h |
Ohio (US) / us-east-2 | 0.5577 USD/h | 1.4362 USD/h |
(MX) / mx-central-1 | 0.622733 USD/h | 1.5078 USD/h |
(TH) / ap-southeast-7 | 0.3879 USD/h | 1.5261 USD/h |
Stockholm (SE) / eu-north-1 | 0.3208 USD/h | 1.5261 USD/h |
(MY) / ap-southeast-5 | 0.612467 USD/h | 1.5261 USD/h |
Aragón (ES) / eu-south-2 | 0.16 USD/h | 1.5997 USD/h |
Dublin (IE) / eu-west-1 | 0.8489 USD/h | 1.6006 USD/h |
Calgary (CA) / ca-west-1 | 0.4342 USD/h | 1.601 USD/h |
Quebec (CA) / ca-central-1 | 0.6885 USD/h | 1.601 USD/h |
London (GB) / eu-west-2 | 0.6356 USD/h | 1.6608 USD/h |
Taipei (TW) / ap-east-2 | 0.517667 USD/h | 1.6694 USD/h |
Milan (IT) / eu-south-1 | 0.443167 USD/h | 1.6755 USD/h |
Paris (FR) / eu-west-3 | 0.732267 USD/h | 1.6755 USD/h |
California (US) / us-west-1 | 1.13485 USD/h | 1.6755 USD/h |
Frankfurt (DE) / eu-central-1 | 0.702567 USD/h | 1.7206 USD/h |
United Arab Emirates / me-central-1 | 0.7208 USD/h | 1.7606 USD/h |
Seoul (KR) / ap-northeast-2 | 0.7612 USD/h | 1.7654 USD/h |
Jakarta (ID) / ap-southeast-3 | 0.324667 USD/h | 1.7952 USD/h |
Melbourne (AU) / ap-southeast-4 | 0.347933 USD/h | 1.7952 USD/h |
Sydney (AU) / ap-southeast-2 | 0.779067 USD/h | 1.7952 USD/h |
Singapore (SG) / ap-southeast-1 | 0.735667 USD/h | 1.7952 USD/h |
Tokyo (JP) / ap-northeast-1 | 0.725267 USD/h | 1.855 USD/h |
Osaka (JP) / ap-northeast-3 | 0.771 USD/h | 1.855 USD/h |
Zurich (CH) / eu-central-2 | 0.4335 USD/h | 1.8925 USD/h |
Cape Town (ZA) / af-south-1 | 0.3479 USD/h | 1.9002 USD/h |
Hong Kong (HK) / ap-east-1 | 0.368767 USD/h | 1.9747 USD/h |
Sao Paulo (BR) / sa-east-1 | 1.635067 USD/h | 2.289 USD/h |
Processor
vCPUs | 32 |
Hypervisor | nitro |
CPU Allocation | Dedicated |
CPU Cores | 32 |
CPU Speed | 2.8 GHz |
CPU Architecture | arm64 |
CPU Manufacturer | AWS |
CPU Family | ARMv9 |
CPU Model | Neoverse-V2 |
CPU L1D Cache | 64 KiB |
CPU L1D Cache Total | 2 MiB |
CPU L1I Cache | 64 KiB |
CPU L1I Cache Total | 2 MiB |
CPU L2 Cache | 2 MiB |
CPU L2 Cache Total | 64 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 | 32 |
Scalability | 100 |
System Resources and Accelerators
| MEMORY | |
|---|---|
Memory Amount | 128 GiB |
Memory Amount Actual | 126 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 | 15 Gbps |
Network Speed Max | 15 Gbps |
Network Storage Speed Baseline | 10 Gbps |
Network Storage Speed Max | 10 Gbps |
Inbound Traffic | 0 GB/month |
Outbound Traffic | 0 GB/month |
IPv4 | 0 |
CPU and System Topology
Server Description
An ARM64 general-purpose server delivering top-tier memory bandwidth and dedicated multi-core performance for database and compilation workloads.
Amazon Web Services m8g.8xlarge is a general-purpose instance powered by 32 dedicated physical cores of the ARMv9-based AWS Graviton Neoverse-V2 processor. Operating at 2.8 GHz, this server features 128.0 GB of RAM, providing a balanced 4.0 GB per core ratio, and runs on the Nitro hypervisor with 15 Gbps baseline network bandwidth. It lacks local storage and GPU accelerators. Benchmark results highlight top-tier memory performance, with uncached large-block read and write bandwidths in the top 10%, alongside strong multi-core execution in software compilation and database operations. However, single-core performance and large-model LLM inference are average to weak. The m8g.8xlarge offers high resource density and qualitative cost efficiency for multi-threaded, memory-intensive applications, making it highly suitable for database hosting, Redis caching, static web serving, and CI/CD compilation pipelines.
Economics
Performance
Memory Bandwidth
Compression
OpenSSL
Geekbench Single-Core
Geekbench Multi-Core
Passmark CPU Scores
| BENCHMARK | SCORE |
|---|---|
Mark | 26328 |
Compression | 212937 |
Encryption | 6065 |
Extended Instructions | 29447 |
Floating Point Maths | 194011 |
Integer Maths | 166984 |
Physics | 8770 |
Prime Numbers | 371 |
Single Threaded | 1942 |
String Sorting | 147182 |
Passmark Memory Scores
| BENCHMARK | SCORE |
|---|---|
Memory Mark | 3209 |
Database Operations | 46696 |
Memory Latency | 50 |
Memory Read Cached | 20799 |
Memory Read Uncached | 19063 |
Memory Write | 21231 |
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
PostgreSQL heavy read-only throughput
Alternatives
Servers of the Same Family
| INSTANCE | vCPUs | MEMORY | GPUs |
|---|---|---|---|
| m8g.medium | 1 | 4 GiB | 0 |
| m8g.large | 2 | 8 GiB | 0 |
| m8g.xlarge | 4 | 16 GiB | 0 |
| m8g.2xlarge | 8 | 32 GiB | 0 |
| m8g.4xlarge | 16 | 64 GiB | 0 |
| m8g.12xlarge | 48 | 192 GiB | 0 |
| m8g.16xlarge | 64 | 256 GiB | 0 |
Similar Servers
| INSTANCE | VENDOR | vCPUs | MEMORY | GPUs |
|---|