c4a-highcpu-64 by Google Cloud Platform

c4a-highcpu-64 is a 64 vCPUs, 128 GB RAM server offered by Google Cloud Platform with 64 vCPUs, 128 GiB of memory and 0 GB of storage. The pricing starts at 0.3738 USD per hour.
64 vCPU
128 GiB Memory
Spare SCore
116,240
(All-cores)
1,819
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
1765209
Name
c4a-highcpu-64
Description
64 vCPUs, 128 GB RAM
Family
c4a
Hw Virt
Average Time To Start
13
Status
active
Observed At
2026-11-08T15:43:43.043049

Availability

REGION / IDSPOTONDEMAND
Columbus (US) / us-east5
0.6591 USD/h 2.4243 USD/h
Council Bluffs (US) / us-central1
1.258 USD/h 2.4243 USD/h
The Dalles (US) / us-west1
1.258 USD/h 2.4243 USD/h
Moncks Corner (US) / us-east1
1.258 USD/h 2.4243 USD/h
Ashburn (US) / us-east4
1.444 USD/h 2.4243 USD/h
Mumbai (IN) / asia-south1
0.9655 USD/h 2.5212 USD/h
Eemshaven (NL) / europe-west4
0.3738 USD/h 2.5454 USD/h
Stockholm (SE) / europe-north2
1.3716 USD/h 2.5454 USD/h
Queretaro (MX) / northamerica-south1
0.7195 USD/h 2.6425 USD/h
Hamina (FI) / europe-north1
0.721 USD/h 2.6694 USD/h
St. Ghislain (BE) / europe-west1
1.1345 USD/h 2.6694 USD/h
Johannesburg (ZA) / africa-south1
1.2038 USD/h 2.6694 USD/h
Toronto (CA) / northamerica-northeast2
1.2264 USD/h 2.6694 USD/h
Montréal (CA) / northamerica-northeast1
1.2273 USD/h 2.6694 USD/h
Las Vegas (US) / us-west4
1.2524 USD/h 2.7305 USD/h
London (GB) / europe-west2
1.4213 USD/h 2.7636 USD/h
Changhua County (TW) / asia-east1
0.9262 USD/h 2.8071 USD/h
Dallas (US) / us-south1
1.0047 USD/h 2.8607 USD/h
Frankfurt (DE) / europe-west3
1.1086 USD/h 2.8607 USD/h
Madrid (ES) / europe-southwest1
1.3343 USD/h 2.8607 USD/h
Los Angeles (US) / us-west2
1.1059 USD/h 2.9143 USD/h
Warsaw (PL) / europe-central2
0.7628 USD/h 2.9333 USD/h
Doha (QA) / me-central1
1.1182 USD/h 2.9456 USD/h
Jurong West (SG) / asia-southeast1
1.7943 USD/h 2.9909 USD/h
Sydney (AU) / australia-southeast1
0.6369 USD/h 3.0308 USD/h
Tokyo (JP) / asia-northeast1
1.5366 USD/h 3.1133 USD/h
Melbourne (AU) / australia-southeast2
0.6621 USD/h 3.1514 USD/h
Zurich (CH) / europe-west6
0.8911 USD/h 3.176 USD/h
Jakarta (ID) / asia-southeast2
0.8495 USD/h 3.26 USD/h
Santiago (CL) / southamerica-west1
1.3756 USD/h 3.4668 USD/h
Osasco (BR) / southamerica-east1
1.462 USD/h 3.8496 USD/h
Dammam (SA) / me-central2
2.3273 USD/h 3.8797 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
63.9
Scalability
99.84

System Resources and Accelerators

MEMORY
Memory Amount
128 GiB
Memory Amount Actual
128 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 dedicated 64-core arm64 processor instance delivering high-throughput memory bandwidth and strong multi-threaded performance for compute-bound workloads.

      Compute OptimizedGeneral Purpose

      Google Cloud Platform c4a-highcpu-64 is an arm64 compute-optimized server featuring 64 dedicated physical cores on the ARMv8 Neoverse-V2 architecture running at 3.0 GHz. It is configured with 128 GB of RAM, providing 2.0 GB of memory per core, and lacks local storage or GPU accelerators. In benchmark evaluations, the instance delivers top-tier multi-core performance, particularly in software compilation, multi-threaded decompression, and Redis SET operations, which reached 134.13 million operations per second. It also exhibits high memory bandwidth, with cached read speeds of 7912.85 GB/sec. However, single-core performance and encryption tests remain in the average tier. The 2.0 GB per core ratio and lack of local storage represent key resource tradeoffs. This instance is suited for compute-intensive, highly parallel workloads such as web serving, compilation pipelines, and physics simulations.

      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) 11,851,533 ops/sec 1,922,940 ops/sec 6.3 50.00% 50.00% +150.00%
      Redis RPS (pipeline=16, SET) 77,514,073 ops/sec 11,797,257 ops/sec 6.5 20.00% 20.00% +45.00%
      PassMark Memory Mark (composite) 3,300 2,406 1.4 10.00% 10.00% +3.40%
      Memory bandwidth (read, 16 MB ~ L3) 383,386 MB/sec 108,657 MB/sec 3.5 10.00% 10.00% +13.00%
      PassMark single-thread CPU 2,077 Mops/s 2,365 Mops/s 0.88 10.00% 10.00% -1.30%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,995

      Geekbench Multi-Core

      Score: 26,801

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 48,479
      Compression
      		 452,754
      Encryption
      		 13,361
      Extended Instructions
      		 83,378
      Floating Point Maths
      		 412,142
      Integer Maths
      		 356,752
      Physics
      		 17,879
      Prime Numbers
      		 704
      Single Threaded
      		 2,077
      String Sorting
      		 311,413

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 3,300
      Database Operations
      		 49,949
      Memory Latency
      		 50
      Memory Read Cached
      		 22,629
      Memory Read Uncached
      		 18,325
      Memory Write
      		 22,774

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 270.44 65.57 0.24×
      bitops
      		 154,802 9,888,933 63.88×
      branch
      		 242,901 15,516,550 63.88×
      funccall
      		 2,110 134,775 63.88×
      funcret
      		 37,550 2,383,675 63.48×
      hash
      		 166,554 10,631,768 63.83×
      intmath
      		 35,049 2,235,298 63.78×
      nop
      		 492,887 31,353,598 63.61×
      prime
      		 531,075 33,841,416 63.72×
      rotate
      		 143,603 9,137,481 63.63×
      str
      		 830,727 52,604,082 63.32×
      wcs
      		 218,600 13,892,111 63.55×
      CryptographySingleMultiScaling
      crypt
      		 3,709 236,871 63.87×
      CompressionSingleMultiScaling
      jpeg
      		 791.02 36,824 46.55×
      zlib
      		 46.26 2,753 59.50×
      HypervisorSingleMultiScaling
      clock
      		 40,562 274,968 6.78×
      clone
      		 458.64 11,926 26.00×
      context
      		 2,639 173,627 65.80×
      cpu-sched
      		 65.79 4,032 61.29×
      eventfd
      		 105,537 2,559,925 24.26×
      fault
      		 23,668 348,996 14.75×
      fork
      		 5,115 119,558 23.37×
      getrandom
      		 65,942 4,214,904 63.92×
      hrtimers
      		 221,449 5,627,295 25.41×
      mprotect
      		 969,732 15,958,609 16.46×
      mtx
      		 8,811,638 3,065,091,566 347.85×
      munmap
      		 3,791 120,654 31.83×
      null
      		 456,214 29,567,574 64.81×
      pipe
      		 1,028,326 32,613,213 31.71×
      priv-instr
      		 817,670 8,356,902 10.22×
      resched
      		 1,655,688 5,836,460 3.53×
      switch
      		 178,296 32,483,876 182.19×
      timermix
      		 556,770 35,451,802 63.67×
      tlb-shootdown
      		 20,501 364,847 17.80×
      vdso
      		 43,398,088 2,770,696,184 63.84×
      vfork
      		 39,706 279,683 7.04×
      yield
      		 80,568,509 84,963,319 1.05×
      zero
      		 2,589,955 166,401,248 64.25×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 2,074 132,508 63.89×
      expmath
      		 392.45 25,069 63.88×
      fma
      		 830,113 52,982,862 63.83×
      fp
      		 165.26 10,454 63.26×
      fractal
      		 8.4 523.73 62.35×
      hyperbolic
      		 379.05 24,210 63.87×
      logmath
      		 459.51 29,362 63.90×
      matrix
      		 7,091 452,915 63.88×
      matrix-3d
      		 1,550 18,133 11.70×
      monte-carlo
      		 204.64 13,288 64.93×
      mpfr
      		 1,531 98,120 64.10×
      powmath
      		 266.51 17,021 63.87×
      trig
      		 509.74 32,542 63.84×
      veccmp
      		 23,343 1,491,319 63.89×
      vecfp
      		 1,327 84,933 64.01×
      vecmath
      		 4,753 303,807 63.92×
      vecshuf
      		 936.9 60,297 64.36×
      vecwide
      		 26,927 1,723,064 63.99×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 9.6 614.78 64.04×
      bsearch
      		 365.38 23,347 63.90×
      bubblesort
      		 1.2 76.8 64.00×
      fibsearch
      		 390.9 24,958 63.85×
      heapsort
      		 14 886.98 63.36×
      hsearch
      		 9,149 578,534 63.23×
      insertionsort
      		 7.4 454 61.35×
      malloc
      		 3,620,135 128,651,939 35.54×
      mcontend
      		 203.71 144,074 707.25×
      mergesort
      		 35.8 2,282 63.75×
      qsort
      		 24.2 1,536 63.45×
      skiplist
      		 7,275 465,178 63.95×
      tree
      		 1.6 51.65 32.28×
      MemorySingleMultiScaling
      cache
      		 483,712 1,615,793 3.34×
      cachehammer
      		 2,035,372 34,143,434 16.78×
      cacheline
      		 73.77 4,747 64.34×
      l1cache
      		 353.63 22,129 62.58×
      memcpy
      		 763.39 48,660 63.74×
      memrate
      		 5.72 57.83 10.11×
      memthrash
      		 242.97 543.53 2.24×
      ptr-chase
      		 24,480,232 537,962,820 21.98×
      spinmem
      		 2,692 54,142 20.11×
      stream
      		 57.94 67,686 1168.21×
      vm
      		 138,857 3,183,011 22.92×

      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-highcpu-64 FAQs