c4a-highmem-64 by Google Cloud Platform

c4a-highmem-64 is a 64 vCPUs, 512 GB RAM server offered by Google Cloud Platform with 64 vCPUs, 512 GiB of memory and 0 GB of storage. The pricing starts at 0.6068 USD per hour.
64 vCPU
512 GiB Memory
Spare SCore
115,713
(All-cores)
1,819
(Single-core)

Specifications #

Server Metadata #

Vendor ID
gcp
Server ID
1765218
Name
c4a-highmem-64
Description
64 vCPUs, 512 GB RAM
Family
General Purpose
Series
c4a
Hw Virt
Average Time To Start
24
Status
active
Observed At
2026-11-17T04:14:20.744956

Availability #

Region / IDSpotOndemand
Columbus (US) / us-east5
0.9253 USD/h
3.7722 USD/h
Council Bluffs (US) / us-central1
2.0461 USD/h
3.7722 USD/h
The Dalles (US) / us-west1
2.0461 USD/h
3.7722 USD/h
Moncks Corner (US) / us-east1
2.0461 USD/h
3.7722 USD/h
Ashburn (US) / us-east4
2.1343 USD/h
3.7722 USD/h
Mumbai (IN) / asia-south1
1.4989 USD/h
3.9228 USD/h
Eemshaven (NL) / europe-west4
0.6068 USD/h
3.9608 USD/h
Stockholm (SE) / europe-north2
2.2309 USD/h
3.9608 USD/h
Queretaro (MX) / northamerica-south1
1.1695 USD/h
4.1117 USD/h
Hamina (FI) / europe-north1
1.1192 USD/h
4.1535 USD/h
St. Ghislain (BE) / europe-west1
1.7608 USD/h
4.1535 USD/h
Johannesburg (ZA) / africa-south1
1.872 USD/h
4.1535 USD/h
Toronto (CA) / northamerica-northeast2
1.9064 USD/h
4.1535 USD/h
Montréal (CA) / northamerica-northeast1
1.9081 USD/h
4.1535 USD/h
Las Vegas (US) / us-west4
1.7585 USD/h
4.2486 USD/h
London (GB) / europe-west2
2.2068 USD/h
4.3 USD/h
Changhua County (TW) / asia-east1
1.4412 USD/h
4.3678 USD/h
Dallas (US) / us-south1
1.4103 USD/h
4.4513 USD/h
Frankfurt (DE) / europe-west3
1.7213 USD/h
4.4513 USD/h
Madrid (ES) / europe-southwest1
2.0718 USD/h
4.4513 USD/h
Los Angeles (US) / us-west2
1.8964 USD/h
4.5345 USD/h
Warsaw (PL) / europe-central2
1.1867 USD/h
4.5643 USD/h
Doha (QA) / me-central1
1.7388 USD/h
4.5832 USD/h
Jurong West (SG) / asia-southeast1
2.7919 USD/h
4.6537 USD/h
Sydney (AU) / australia-southeast1
0.9906 USD/h
4.7158 USD/h
Tokyo (JP) / asia-northeast1
2.1577 USD/h
4.8442 USD/h
Melbourne (AU) / australia-southeast2
1.03 USD/h
4.9024 USD/h
Zurich (CH) / europe-west6
1.3853 USD/h
4.9415 USD/h
Jakarta (ID) / asia-southeast2
1.3207 USD/h
5.0724 USD/h
Santiago (CL) / southamerica-west1
2.1386 USD/h
5.394 USD/h
Osasco (BR) / southamerica-east1
2.273 USD/h
5.9898 USD/h

Processor #

vCPUs
64
CPU Allocation
Dedicated
CPU Cores
64
CPU Speed
3 GHz
CPU Architecture
arm64
CPU Family
ARMv8
CPU Model
Neoverse-V2
CPU L1D Cache
64 KiB
CPU L1D Cache Total
4 MiB
CPU L1I Cache
64 KiB
CPU L1I Cache Total
4 MiB
CPU L2 Cache
2 MiB
CPU L2 Cache Total
128 MiB
CPU L3 Cache
80 MiB
CPU L3 Cache Total
80 MiB
CPU Flags
fp, asimd, evtstrm, aes, pmull, sha1, sha2, crc32, atomics, fphp, asimdhp, cpuid, asimdrdm, jscvt, fcma, lrcpc, dcpop, sha3, sm3, sm4, asimddp, sha512, sve, asimdfhm, dit, uscat, ilrcpc, flagm, sb, paca, pacg, dcpodp, sve2, sveaes, svepmull, svebitperm, svesha3, svesm4, flagm2, frint, svei8mm, svebf16, i8mm, bf16, dgh, rng, bti
Ecpus
63.6
Scalability
99.38

System Resources and Accelerators #

Memory
Memory Amount
512 GiB
Memory Amount Actual
512 GiB
Accelerators
Accelerator Count
0
Accelerator Memory Min
0 MiB
Accelerator Memory Total
0 MiB
Accelerators
    Storage
    Storage Size
    0 GB
    Storages
      Compatible Storage IDs
      30014, 30017, 30012, 30013, 30016
      Network
      Inbound Traffic
      0 GB/month
      Outbound Traffic
      0 GB/month
      IPv4
      0

      CPU and System Topology #

      Server Description #

      An ARM-powered memory-optimized server featuring sixty-four dedicated cores and high-bandwidth memory for demanding database and compilation workloads.

      Google Cloud Platform c4a-highmem-64 is an ARM-based server instance designed for memory-intensive workloads. It features 64 dedicated physical cores on the ARMv8 Neoverse-V2 architecture running at 3.0 GHz, paired with 512.0 GB of RAM, yielding 8.0 GB of memory per core. The instance lacks local storage and GPU accelerators. Performance benchmarks show top-tier capabilities in multi-core processing, software compilation, and memory bandwidth, with cached read-only small block speeds reaching 7912.04 GB/sec. Database operations, Redis SET throughput, and static web serving also perform in the top tier, while single-core execution remains average. This hardware profile offers high resource density and qualitative cost efficiency for memory-bound applications. It is highly suited for database hosting, large-scale caching, software build pipelines, and multi-threaded data processing.

      Economics #

      Average Price per Region #

      Prices per Zone #

      Lowest Prices #

      Performance #

      Workload Profiles #

      4.2Score
      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) 12,137,444 ops/sec 1,933,252 ops/sec 6.3 50.00% 50.00% +150.00%
      Redis RPS (pipeline=16, SET) 76,514,202 ops/sec 11,814,424 ops/sec 6.4 20.00% 20.00% +45.00%
      PassMark Memory Mark (composite) 3,278 2,408 1.4 10.00% 10.00% +3.40%
      Memory bandwidth (read, 16 MB ~ L3) 396,094 MB/sec 108,674 MB/sec 3.6 10.00% 10.00% +14.00%
      PassMark single-thread CPU 2,076 Mops/s 2,365 Mops/s 0.88 10.00% 10.00% -1.30%

      Memory Bandwidth#

      Compression #

      OpenSSL #

      Geekbench Single-Core #

      Score: 1,994

      Geekbench Multi-Core #

      Score: 26,681

      Passmark CPU Scores #

      BENCHMARKSCORE
      Mark
      48,473
      Compression
      452,849
      Encryption
      13,363
      Extended Instructions
      83,356
      Floating Point Maths
      412,162
      Integer Maths
      356,851
      Physics
      17,661
      Prime Numbers
      708
      Single Threaded
      2,076
      String Sorting
      310,981

      Passmark Memory Scores #

      BENCHMARKSCORE
      Memory Mark
      3,278
      Database Operations
      49,962
      Memory Latency
      51
      Memory Read Cached
      21,755
      Memory Read Uncached
      18,914
      Memory Write
      22,772

      Stress-ng Stressors #

      CPU integerSingleMultiScaling
      atomic
      249.65 105.55 0.42×
      bitops
      154,933 9,883,323 63.79×
      branch
      242,916 15,511,944 63.86×
      funccall
      2,112 134,741 63.81×
      funcret
      36,767 2,388,848 64.97×
      hash
      166,611 10,629,512 63.80×
      intmath
      34,945 2,231,525 63.86×
      nop
      490,209 31,433,224 64.12×
      prime
      530,200 33,865,201 63.87×
      rotate
      142,558 9,157,388 64.24×
      str
      830,815 52,668,776 63.39×
      wcs
      219,504 13,893,360 63.29×
      CryptographySingleMultiScaling
      crypt
      3,702 236,753 63.96×
      CompressionSingleMultiScaling
      jpeg
      793.35 36,776 46.36×
      zlib
      34.56 2,816 81.49×
      HypervisorSingleMultiScaling
      clock
      38,322 278,948 7.28×
      clone
      456.76 8,103 17.74×
      context
      2,637 174,036 65.99×
      cpu-sched
      65.53 4,076 62.20×
      eventfd
      111,749 2,505,311 22.42×
      fault
      22,929 329,610 14.38×
      fork
      5,313 119,991 22.58×
      getrandom
      66,009 4,213,178 63.83×
      hrtimers
      264,201 7,705,209 29.16×
      mprotect
      1,009,621 16,810,027 16.65×
      mtx
      10,236,859 2,803,113,119 273.83×
      munmap
      3,747 117,671 31.40×
      null
      458,068 29,514,274 64.43×
      pipe
      1,109,406 33,889,048 30.55×
      priv-instr
      811,859 9,015,458 11.10×
      resched
      2,745,170 5,609,262 2.04×
      switch
      172,494 32,639,735 189.22×
      timermix
      557,975 35,501,739 63.63×
      tlb-shootdown
      17,201 362,857 21.10×
      vdso
      43,684,330 2,782,087,226 63.69×
      vfork
      40,229 270,605 6.73×
      yield
      81,332,227 84,329,264 1.04×
      zero
      2,589,807 166,380,419 64.24×
      CPU float/SIMDSingleMultiScaling
      eigen
      2,074 132,446 63.86×
      expmath
      392.49 25,050 63.82×
      fma
      830,517 52,965,292 63.77×
      fp
      167.12 10,443 62.49×
      fractal
      8.4 523.74 62.35×
      hyperbolic
      379.08 24,192 63.82×
      logmath
      459.65 29,334 63.82×
      matrix
      7,088 452,459 63.83×
      matrix-3d
      1,504 19,119 12.71×
      monte-carlo
      204.62 13,260 64.80×
      mpfr
      1,534 98,432 64.18×
      powmath
      266.44 17,023 63.89×
      trig
      509.53 32,558 63.90×
      veccmp
      23,354 1,491,329 63.86×
      vecfp
      1,330 85,088 63.99×
      vecmath
      4,758 303,170 63.72×
      vecshuf
      943.91 59,854 63.41×
      vecwide
      26,991 1,853,115 68.66×
      AlgorithmsSingleMultiScaling
      bitonicsort
      9.8 615.99 62.86×
      bsearch
      366.36 23,356 63.75×
      bubblesort
      1.2 76.8 64.00×
      fibsearch
      391.23 24,967 63.82×
      heapsort
      13.8 882.98 63.98×
      hsearch
      9,063 578,818 63.86×
      insertionsort
      6.6 446.6 67.67×
      malloc
      3,716,941 125,395,584 33.74×
      mcontend
      224.65 143,913 640.61×
      mergesort
      35.8 2,278 63.63×
      qsort
      24.2 1,536 63.45×
      skiplist
      7,283 465,354 63.90×
      tree
      1.6 55.63 34.77×
      MemorySingleMultiScaling
      cache
      463,545 1,615,370 3.48×
      cachehammer
      2,051,844 37,669,737 18.36×
      cacheline
      71.77 4,484 62.48×
      l1cache
      353.69 22,031 62.29×
      memcpy
      766.04 48,840 63.76×
      memrate
      5.72 56.62 9.90×
      memthrash
      240.73 545.22 2.26×
      ptr-chase
      22,979,378 544,090,243 23.68×
      spinmem
      3,382 52,617 15.56×
      stream
      57.98 72,162 1244.60×
      vm
      144,625 3,102,743 21.45×

      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
      c4a-highcpu-1 12 GiB0
      c4a-standard-1 14 GiB0
      c4a-highmem-1 18 GiB0
      c4a-highcpu-2 24 GiB0
      c4a-standard-2 28 GiB0
      c4a-highmem-2 216 GiB0
      c4a-highcpu-4 48 GiB0

      Similar Servers #

      INSTANCEVENDORvCPUsMEMORYAccelerators

      c4a-highmem-64 FAQs #