t2a-standard-4 by Google Cloud Platform

t2a-standard-4 is a 4 vCPUs, 16 GB RAM server offered by Google Cloud Platform with 4 vCPUs, 16 GiB of memory and 0 GB of storage. The pricing starts at 0.0644 USD per hour.
4 vCPU
16 GiB Memory
Spare SCore
7,218
(All-cores)
1,813
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
1220003
Name
t2a-standard-4
Description
4 vCPUs, 16 GB RAM
Family
t2a
Hw Virt
Average Time To Start
14
Status
active
Observed At
2026-10-24T15:52:24.393153

Availability

REGION / IDSPOTONDEMAND
Council Bluffs (US) / us-central1
0.0792 USD/h 0.154 USD/h
Eemshaven (NL) / europe-west4
0.0966 USD/h 0.1618 USD/h
Jurong West (SG) / asia-southeast1
0.0644 USD/h 0.1899 USD/h

Processor

vCPUs
4
CPU Allocation
Dedicated
CPU Cores
4
CPU Speed
3 GHz
CPU Architecture
arm64
CPU Manufacturer
Ampere
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
ACCELERATORS
Accelerator Count
0
Accelerator Memory Min
0 MiB
Accelerator Memory Total
0 MiB
Accelerators
    STORAGE
    Storage Size
    0 GB
    Storages
      NETWORK
      Inbound Traffic
      0 GB/month
      Outbound Traffic
      0 GB/month
      IPv4
      0

      CPU and System Topology

      Server Description

      A balanced ARM64 virtual machine featuring dedicated Ampere Altra cores for general-purpose workloads and cost-efficient application development.

      General Purpose

      Google Cloud Platform t2a-standard-4 is an ARM64-based general-purpose instance configured with 4 dedicated physical cores of an Ampere Altra ARMv8 Neoverse-N1 processor running at 3.0 GHz. It includes 16 GB of system memory, yielding 4 GB of RAM per core, with no local storage or GPU hardware. Performance benchmarks indicate average capabilities in stress-ng CPU tests and database operations, but show weaknesses in single-threaded compression, software compilation, and static web serving. Cryptographic and LLM inference tasks perform poorly due to the lack of specialized instruction sets like AVX. This instance is qualitatively cost-efficient for standard ARM64 development, basic database hosting, and general-purpose utility workloads that do not require high-performance local storage or intensive mathematical acceleration.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      0.33Score
      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) 501,424 ops/sec 1,919,289 ops/sec 0.26 50.00% 50.00% -49.00%
      Redis RPS (pipeline=16, SET) 3,244,612 ops/sec 11,728,058 ops/sec 0.27 20.00% 20.00% -23.00%
      PassMark Memory Mark (composite) 1,643 2,416 0.67 10.00% 10.00% -3.90%
      Memory bandwidth (read, 16 MB ~ L3) 52,113 MB/sec 108,466 MB/sec 0.47 10.00% 10.00% -7.30%
      PassMark single-thread CPU 1,320 Mops/s 2,365 Mops/s 0.54 10.00% 10.00% -6.00%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,062

      Geekbench Multi-Core

      Score: 3,517

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 3,191
      Compression
      		 21,860
      Encryption
      		 649
      Extended Instructions
      		 2,957
      Floating Point Maths
      		 14,237
      Integer Maths
      		 18,776
      Physics
      		 652
      Prime Numbers
      		 36
      Single Threaded
      		 1,320
      String Sorting
      		 13,498

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 1,643
      Database Operations
      		 2,851
      Memory Latency
      		 71
      Memory Read Cached
      		 11,289
      Memory Read Uncached
      		 8,671
      Memory Write
      		 14,816

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 87.21 96.97 1.11×
      bitops
      		 107,790 429,339 3.98×
      branch
      		 218,213 869,549 3.98×
      funccall
      		 1,329 5,291 3.98×
      funcret
      		 20,696 82,116 3.97×
      hash
      		 126,632 505,234 3.99×
      intmath
      		 30,596 122,788 4.01×
      nop
      		 172,355 685,705 3.98×
      prime
      		 334,384 1,331,284 3.98×
      rotate
      		 95,695 380,905 3.98×
      str
      		 511,780 2,033,828 3.97×
      wcs
      		 118,317 471,622 3.99×
      CryptographySingleMultiScaling
      crypt
      		 2,875 11,489 4.00×
      CompressionSingleMultiScaling
      jpeg
      		 514 2,032 3.95×
      zlib
      		 43.02 141.21 3.28×
      HypervisorSingleMultiScaling
      clock
      		 35,567 119,295 3.35×
      clone
      		 299.24 678.36 2.27×
      context
      		 2,594 10,317 3.98×
      cpu-sched
      		 64.51 272.41 4.22×
      eventfd
      		 65,068 358,943 5.52×
      fault
      		 12,805 40,989 3.20×
      fork
      		 3,829 13,615 3.56×
      getrandom
      		 47,640 190,025 3.99×
      hrtimers
      		 292,877 426,836 1.46×
      mprotect
      		 933,771 1,319,656 1.41×
      mtx
      		 8,507,179 163,660,046 19.24×
      munmap
      		 2,485 9,103 3.66×
      null
      		 459,589 1,827,614 3.98×
      pipe
      		 684,799 2,370,099 3.46×
      priv-instr
      		 722,045 2,672,838 3.70×
      resched
      		 1,117,021 563,726 0.50×
      switch
      		 130,976 1,178,742 9.00×
      timermix
      		 345,170 1,372,306 3.98×
      tlb-shootdown
      		 5,717 7,055 1.23×
      vdso
      		 46,408,231 184,894,293 3.98×
      vfork
      		 28,283 73,720 2.61×
      yield
      		 3,197,154 3,359,844 1.05×
      zero
      		 1,730,580 6,890,565 3.98×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 1,324 5,276 3.99×
      expmath
      		 238.09 948.77 3.98×
      fma
      		 635,886 2,533,921 3.98×
      fp
      		 103.2 406.59 3.94×
      fractal
      		 6.6 25.6 3.88×
      hyperbolic
      		 242.52 965.41 3.98×
      logmath
      		 291.37 1,160 3.98×
      matrix
      		 5,291 21,085 3.99×
      matrix-3d
      		 477.59 1,878 3.93×
      monte-carlo
      		 192.92 770.8 4.00×
      mpfr
      		 635.05 2,532 3.99×
      powmath
      		 174.97 696.9 3.98×
      trig
      		 326.8 1,301 3.98×
      veccmp
      		 16,915 67,581 4.00×
      vecfp
      		 739.48 2,951 3.99×
      vecmath
      		 3,066 12,212 3.98×
      vecshuf
      		 667.04 2,654 3.98×
      vecwide
      		 18,257 72,691 3.98×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 5.4 21.4 3.96×
      bsearch
      		 256.19 1,020 3.98×
      bubblesort
      		 0.8 3.2 4.00×
      fibsearch
      		 271.38 1,080 3.98×
      heapsort
      		 8.2 32.6 3.98×
      hsearch
      		 4,884 19,304 3.95×
      insertionsort
      		 4.4 17.8 4.05×
      malloc
      		 2,393,574 10,451,370 4.37×
      mcontend
      		 293.17 7,393 25.22×
      mergesort
      		 27.2 109.99 4.04×
      qsort
      		 19.2 76.6 3.99×
      skiplist
      		 5,310 21,140 3.98×
      tree
      		 1.2 4 3.33×
      MemorySingleMultiScaling
      cache
      		 266,026 327,483 1.23×
      cachehammer
      		 204,202 547,418 2.68×
      cacheline
      		 40.92 178.25 4.36×
      l1cache
      		 180.72 720.04 3.98×
      memcpy
      		 440.16 1,753 3.98×
      memrate
      		 3.15 11 3.49×
      memthrash
      		 103.32 122.99 1.19×
      ptr-chase
      		 12,569,468 43,675,513 3.47×
      spinmem
      		 1,048 - -
      stream
      		 65.98 879.13 13.32×
      vm
      		 59,257 264,838 4.47×

      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

      INSTANCEvCPUsMEMORYAccelerators
      t2a-standard-1 14 GiB0
      t2a-standard-2 28 GiB0
      t2a-standard-8 832 GiB0
      t2a-standard-16 1664 GiB0
      t2a-standard-32 32128 GiB0
      t2a-standard-48 48192 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      t2a-standard-4 FAQs