t4g.xlarge by Amazon Web Services
(All-cores)
(Single-core)
Specifications
Server Metadata
Vendor ID | aws |
Name | t4g.xlarge |
Description | Burstable performance [AWS Graviton processors] Gen4 xlarge |
Family | t4g |
Hw Virt | |
Average Time To Start | 8 |
Status | active |
Observed At | 2026-09-15T20:36:04.780773 |
Availability
| REGION / ID | SPOT | ONDEMAND |
|---|---|---|
Hyderabad (IN) / ap-south-2 | 0.0278 USD/h | 0.0896 USD/h |
Mumbai (IN) / ap-south-1 | 0.0378 USD/h | 0.0896 USD/h |
Ohio (US) / us-east-2 | 0.055733 USD/h | 0.1344 USD/h |
Northern Virgina (US) / us-east-1 | 0.07242 USD/h | 0.1344 USD/h |
Oregon (US) / us-west-2 | 0.090925 USD/h | 0.1344 USD/h |
Stockholm (SE) / eu-north-1 | 0.034467 USD/h | 0.1376 USD/h |
(MX) / mx-central-1 | 0.06 USD/h | 0.1411 USD/h |
Aragón (ES) / eu-south-2 | 0.027167 USD/h | 0.1472 USD/h |
Calgary (CA) / ca-west-1 | 0.035667 USD/h | 0.1472 USD/h |
Quebec (CA) / ca-central-1 | 0.069867 USD/h | 0.1472 USD/h |
Dublin (IE) / eu-west-1 | 0.078967 USD/h | 0.1472 USD/h |
London (GB) / eu-west-2 | 0.056875 USD/h | 0.1504 USD/h |
Paris (FR) / eu-west-3 | 0.063533 USD/h | 0.1504 USD/h |
(TH) / ap-southeast-7 | 0.0602 USD/h | 0.1526 USD/h |
(MY) / ap-southeast-5 | 0.069933 USD/h | 0.1526 USD/h |
Milan (IT) / eu-south-1 | 0.0558 USD/h | 0.1536 USD/h |
Frankfurt (DE) / eu-central-1 | 0.085967 USD/h | 0.1536 USD/h |
Tel Aviv (IL) / il-central-1 | 0.040467 USD/h | 0.1546 USD/h |
Taipei (TW) / ap-east-2 | 0.0779 USD/h | 0.1555 USD/h |
California (US) / us-west-1 | 0.07835 USD/h | 0.16 USD/h |
Seoul (KR) / ap-northeast-2 | 0.05445 USD/h | 0.1664 USD/h |
Zurich (CH) / eu-central-2 | 0.0541 USD/h | 0.169 USD/h |
Jakarta (ID) / ap-southeast-3 | 0.0378 USD/h | 0.1696 USD/h |
Melbourne (AU) / ap-southeast-4 | 0.0402 USD/h | 0.1696 USD/h |
Sydney (AU) / ap-southeast-2 | 0.0795 USD/h | 0.1696 USD/h |
Singapore (SG) / ap-southeast-1 | 0.0951 USD/h | 0.1696 USD/h |
Tokyo (JP) / ap-northeast-1 | 0.0791 USD/h | 0.1728 USD/h |
Cape Town (ZA) / af-south-1 | 0.0553 USD/h | 0.1734 USD/h |
Osaka (JP) / ap-northeast-3 | 0.0516 USD/h | 0.1741 USD/h |
(NZ) / ap-southeast-6 | 0.055 USD/h | 0.1782 USD/h |
Hong Kong (HK) / ap-east-1 | 0.0631 USD/h | 0.1856 USD/h |
Sao Paulo (BR) / sa-east-1 | 0.0579 USD/h | 0.2144 USD/h |
Processor
vCPUs | 4 |
Hypervisor | nitro |
CPU Allocation | Burstable |
CPU Cores | 4 |
CPU Speed | 2.5 GHz |
CPU Architecture | arm64 |
CPU Manufacturer | AWS |
CPU Family | ARMv8 |
CPU Model | Neoverse-N1 |
CPU L1D Cache | 64 KiB |
CPU L1D Cache Total | 256 KiB |
CPU L1I Cache | 64 KiB |
CPU L1I Cache Total | 256 KiB |
CPU L2 Cache | 1 MiB |
CPU L2 Cache Total | 4 MiB |
CPU L3 Cache | 32 MiB |
CPU L3 Cache Total | 32 MiB |
CPU Flags | fp, asimd, evtstrm, aes, pmull, sha1, sha2, crc32, atomics, fphp, asimdhp, cpuid, asimdrdm, lrcpc, dcpop, asimddp, ssbs |
Ecpus | 4 |
Scalability | 100 |
System Resources and Accelerators
| MEMORY | |
|---|---|
Memory Amount | 16 GiB |
Memory Amount Actual | 16 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 | 1.024 Gbps |
Network Speed Max | 5 Gbps |
Network Storage Speed Baseline | 0.695 Gbps |
Network Storage Speed Max | 2.78 Gbps |
Inbound Traffic | 0 GB/month |
Outbound Traffic | 0 GB/month |
IPv4 | 0 |
CPU and System Topology
Server Description
A budget-friendly, burstable ARM64 virtual machine offering balanced memory and compute resources for workloads with variable CPU utilization.
Amazon Web Services t4g.xlarge is a burstable, general-purpose instance powered by a 4-core AWS Graviton Neoverse-N1 ARMv8 processor running at 2.5 GHz. Built on the Nitro hypervisor, it features 16.0 GB of RAM, a 1 Gbps baseline network speed, and no local storage or GPU. The instance delivers average single-core CPU performance and large-block memory bandwidth, though multi-core and complex decompression tasks show weaker benchmark results. Lacking AVX and AMX extensions, it is not designed for heavy vector math or machine learning. Instead, its burstable CPU allocation makes it a highly cost-efficient option for workloads with variable demand. It is best suited for static web serving, Redis caching, development environments, and lightweight database operations that benefit from a balanced memory-to-vCPU ratio without requiring continuous maximum CPU utilization.
Economics
Performance
Memory Bandwidth
Compression
OpenSSL
Geekbench Single-Core
Geekbench Multi-Core
Passmark CPU Scores
| BENCHMARK | SCORE |
|---|---|
Mark | 2676 |
Compression | 18402 |
Encryption | 541 |
Extended Instructions | 2465 |
Floating Point Maths | 11954 |
Integer Maths | 15744 |
Physics | 599 |
Prime Numbers | 29 |
Single Threaded | 1109 |
String Sorting | 11387 |
Passmark Memory Scores
| BENCHMARK | SCORE |
|---|---|
Memory Mark | 1563 |
Database Operations | 2582 |
Memory Latency | 72 |
Memory Read Cached | 9456 |
Memory Read Uncached | 9125 |
Memory Write | 12317 |
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 |
|---|---|---|---|
| t4g.nano | 2 | 0.5 GiB | 0 |
| t4g.micro | 2 | 1 GiB | 0 |
| t4g.small | 2 | 2 GiB | 0 |
| t4g.medium | 2 | 4 GiB | 0 |
| t4g.large | 2 | 8 GiB | 0 |
| t4g.2xlarge | 8 | 32 GiB | 0 |
Similar Servers
| INSTANCE | VENDOR | vCPUs | MEMORY | GPUs |
|---|