t4g.2xlarge by Amazon Web Services

t4g.2xlarge is a Burstable performance [AWS Graviton processors] Gen4 2xlarge server offered by Amazon Web Services with 8 vCPUs, 32 GiB of memory and 0 GB of storage. The pricing starts at 0.0179 USD per hour.
8 vCPU
32 GiB Memory
Spare SCore
12,133
(All-cores)
1,520
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
t4g.2xlarge
Description
Burstable performance [AWS Graviton processors] Gen4 2xlarge
Family
t4g
Hw Virt
Average Time To Start
9
Status
active
Observed At
2026-11-07T19:46:52.265574

Availability

REGION / IDSPOTONDEMAND
Hyderabad (IN) / ap-south-2
0.0179 USD/h 0.1792 USD/h
Mumbai (IN) / ap-south-1
0.091167 USD/h 0.1792 USD/h
Northern Virgina (US) / us-east-1
0.11926 USD/h 0.2688 USD/h
Ohio (US) / us-east-2
0.1019 USD/h 0.2688 USD/h
Oregon (US) / us-west-2
0.133 USD/h 0.2688 USD/h
Stockholm (SE) / eu-north-1
0.068 USD/h 0.2752 USD/h
(MX) / mx-central-1
0.078567 USD/h 0.2822 USD/h
Aragón (ES) / eu-south-2
0.034067 USD/h 0.2944 USD/h
Calgary (CA) / ca-west-1
0.0754 USD/h 0.2944 USD/h
Dublin (IE) / eu-west-1
0.155467 USD/h 0.2944 USD/h
Quebec (CA) / ca-central-1
0.184 USD/h 0.2944 USD/h
London (GB) / eu-west-2
0.113375 USD/h 0.3008 USD/h
Paris (FR) / eu-west-3
0.129 USD/h 0.3008 USD/h
(MY) / ap-southeast-5
0.1172 USD/h 0.3053 USD/h
(TH) / ap-southeast-7
0.123267 USD/h 0.3053 USD/h
Milan (IT) / eu-south-1
0.070767 USD/h 0.3072 USD/h
Frankfurt (DE) / eu-central-1
0.136367 USD/h 0.3072 USD/h
Tel Aviv (IL) / il-central-1
0.1281 USD/h 0.3091 USD/h
Taipei (TW) / ap-east-2
0.131433 USD/h 0.311 USD/h
California (US) / us-west-1
0.11695 USD/h 0.32 USD/h
Seoul (KR) / ap-northeast-2
0.1242 USD/h 0.3328 USD/h
Zurich (CH) / eu-central-2
0.106033 USD/h 0.3379 USD/h
Jakarta (ID) / ap-southeast-3
0.0339 USD/h 0.3392 USD/h
Melbourne (AU) / ap-southeast-4
0.078467 USD/h 0.3392 USD/h
Sydney (AU) / ap-southeast-2
0.1318 USD/h 0.3392 USD/h
Singapore (SG) / ap-southeast-1
0.175267 USD/h 0.3392 USD/h
Tokyo (JP) / ap-northeast-1
0.1318 USD/h 0.3456 USD/h
Cape Town (ZA) / af-south-1
0.131233 USD/h 0.3469 USD/h
Osaka (JP) / ap-northeast-3
0.1129 USD/h 0.3482 USD/h
(NZ) / ap-southeast-6
0.106167 USD/h 0.3565 USD/h
Hong Kong (HK) / ap-east-1
0.096667 USD/h 0.3712 USD/h
Sao Paulo (BR) / sa-east-1
0.105767 USD/h 0.4288 USD/h

Processor

vCPUs
8
Hypervisor
nitro
CPU Allocation
Burstable
CPU Cores
8
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
512 KiB
CPU L1I Cache
64 KiB
CPU L1I Cache Total
512 KiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
8 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
8
Scalability
100

System Resources and Accelerators

MEMORY
Memory Amount
32 GiB
Memory Amount Actual
32 GiB
ACCELERATORS
Accelerator Count
0
Accelerator Memory Min
0 MiB
Accelerator Memory Total
0 MiB
Accelerators
    STORAGE
    Storage Size
    0 GB
    Storages
      NETWORK
      Network Speed Baseline
      2.048 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 burstable arm64 instance delivering balanced memory and multi-core performance for workloads with variable CPU utilization.

      Burstable & BudgetGeneral Purpose

      Amazon Web Services t4g.2xlarge is a burstable, arm64-based instance powered by an 8-core AWS Graviton Neoverse-N1 processor running at 2.5 GHz. It features 32.0 GB of RAM, a 2 Gbps baseline network bandwidth, and operates on the Nitro hypervisor without local storage or GPU accelerators. Benchmarks indicate average performance for multi-core processing, database operations, and static web serving, though single-threaded tasks and LLM inference show weaker results. It achieves 9.35 million operations per second in Redis SET tests and an average of 12133.02 in stress-ng multi-core tests. This instance provides a cost-efficient option for workloads with variable CPU demands, such as web serving, software compilation, and medium-scale database applications.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      0.52Score
      Precomputed compound score for Cache Intensive workloads. A weighted average (geometric mean) of benchmark scores compared to their medians: score = ∏ (x_i / m_i)^(w_i / Σw). The score of 1.0 represents a synthetic baseline server with the median performance of each component benchmark; 0.5 means roughly half the performance; and 2.0 means twice the performance of that reference profile. Component weights: 50% Redis RPS (pipeline=1, SET), 20% Redis RPS (pipeline=16, SET), 10% PassMark Memory Mark (composite), 10% Memory bandwidth (read, 16 MB ~ L3), 10% PassMark single-thread CPU. Rationale for component selection: In-memory key-value store workload, mixing direct Redis performance metrics with memory speed and latency benchmarks, and single-core CPU performance profiles.
      Component Score Weight Impact
      Raw Reference Normalized Target Actual
      Redis RPS (pipeline=1, SET) 884,396 ops/sec 1,922,940 ops/sec 0.46 50.00% 50.00% -32.00%
      Redis RPS (pipeline=16, SET) 5,241,127 ops/sec 11,797,257 ops/sec 0.43 20.00% 20.00% -16.00%
      PassMark Memory Mark (composite) 1,614 2,406 0.67 10.00% 10.00% -3.90%
      Memory bandwidth (read, 16 MB ~ L3) 133,858 MB/sec 108,657 MB/sec 1.2 10.00% 10.00% +1.80%
      PassMark single-thread CPU 1,109 Mops/s 2,365 Mops/s 0.46 10.00% 10.00% -7.50%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 877

      Geekbench Multi-Core

      Score: 5,149

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 5,230
      Compression
      		 37,704
      Encryption
      		 1,091
      Extended Instructions
      		 4,972
      Floating Point Maths
      		 24,006
      Integer Maths
      		 31,534
      Physics
      		 1,072
      Prime Numbers
      		 60
      Single Threaded
      		 1,109
      String Sorting
      		 22,806

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 1,614
      Database Operations
      		 5,171
      Memory Latency
      		 85
      Memory Read Cached
      		 9,471
      Memory Read Uncached
      		 9,049
      Memory Write
      		 12,366

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 123.47 98.76 0.80×
      bitops
      		 89,912 719,183 8.00×
      branch
      		 179,335 1,459,292 8.14×
      funccall
      		 1,111 8,843 7.96×
      funcret
      		 17,225 137,639 7.99×
      hash
      		 106,432 848,055 7.97×
      intmath
      		 25,568 208,785 8.17×
      nop
      		 144,194 1,147,241 7.96×
      prime
      		 284,192 2,262,815 7.96×
      rotate
      		 80,262 637,239 7.94×
      str
      		 428,867 3,419,402 7.97×
      wcs
      		 99,187 789,996 7.96×
      CryptographySingleMultiScaling
      crypt
      		 2,413 19,202 7.96×
      CompressionSingleMultiScaling
      jpeg
      		 430.22 3,459 8.04×
      zlib
      		 15.03 262.95 17.50×
      HypervisorSingleMultiScaling
      clock
      		 27,178 181,726 6.69×
      clone
      		 247.98 1,247 5.03×
      context
      		 2,201 17,606 8.00×
      cpu-sched
      		 65.77 516.67 7.86×
      eventfd
      		 30,856 447,805 14.51×
      fault
      		 10,782 75,201 6.97×
      fork
      		 3,408 23,604 6.93×
      getrandom
      		 40,131 319,577 7.96×
      hrtimers
      		 268,606 790,354 2.94×
      mprotect
      		 944,167 2,295,364 2.43×
      mtx
      		 10,263,115 208,533,508 20.32×
      munmap
      		 2,442 17,742 7.27×
      null
      		 385,031 3,056,918 7.94×
      pipe
      		 679,385 3,669,823 5.40×
      priv-instr
      		 612,028 4,535,396 7.41×
      resched
      		 2,593,439 1,151,969 0.44×
      switch
      		 45,972 1,838,126 39.98×
      timermix
      		 280,406 2,226,729 7.94×
      tlb-shootdown
      		 4,491 7,395 1.65×
      vdso
      		 41,264,578 329,155,621 7.98×
      vfork
      		 19,588 109,768 5.60×
      yield
      		 5,618,503 5,869,880 1.04×
      zero
      		 1,720,625 13,677,005 7.95×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 1,105 8,841 8.00×
      expmath
      		 198.08 1,585 8.00×
      fma
      		 530,655 4,227,036 7.97×
      fp
      		 83.76 687 8.20×
      fractal
      		 5.4 42.8 7.93×
      hyperbolic
      		 201.79 1,618 8.02×
      logmath
      		 244.23 1,941 7.95×
      matrix
      		 4,417 35,391 8.01×
      matrix-3d
      		 493.6 3,794 7.69×
      monte-carlo
      		 160.83 1,288 8.01×
      mpfr
      		 533.43 4,241 7.95×
      powmath
      		 146.65 1,170 7.98×
      trig
      		 274.04 2,187 7.98×
      veccmp
      		 14,280 113,839 7.97×
      vecfp
      		 620.15 4,950 7.98×
      vecmath
      		 2,569 20,493 7.98×
      vecshuf
      		 558.67 4,436 7.94×
      vecwide
      		 14,882 121,645 8.17×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 4.4 35 7.95×
      bsearch
      		 213.78 1,708 7.99×
      bubblesort
      		 0.6 4.8 8.00×
      fibsearch
      		 227.3 1,813 7.97×
      heapsort
      		 7 54.2 7.74×
      hsearch
      		 4,083 32,457 7.95×
      insertionsort
      		 3.8 30.4 8.00×
      malloc
      		 2,193,632 17,725,044 8.08×
      mcontend
      		 265.41 12,309 46.38×
      mergesort
      		 22.8 184.99 8.11×
      qsort
      		 16.2 129.39 7.99×
      skiplist
      		 4,454 35,531 7.98×
      tree
      		 1 6.4 6.40×
      MemorySingleMultiScaling
      cache
      		 328,693 540,078 1.64×
      cachehammer
      		 83,763 215,082 2.57×
      cacheline
      		 53.88 421.99 7.83×
      l1cache
      		 151.04 1,208 8.00×
      memcpy
      		 369.38 2,940 7.96×
      memrate
      		 3.33 20.27 6.09×
      memthrash
      		 85.9 172.75 2.01×
      ptr-chase
      		 11,098,862 78,425,265 7.07×
      spinmem
      		 415.18 474.29 1.14×
      stream
      		 81.06 3,535 43.61×
      vm
      		 55,924 516,369 9.23×

      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

      INSTANCEvCPUsMEMORYAccelerators
      t4g.nano 20.5 GiB0
      t4g.micro 21 GiB0
      t4g.small 22 GiB0
      t4g.medium 24 GiB0
      t4g.large 28 GiB0
      t4g.xlarge 416 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      t4g.2xlarge FAQs