c4a-highmem-48 by Google Cloud Platform

c4a-highmem-48 is a 48 vCPUs, 384 GB RAM server offered by Google Cloud Platform with 48 vCPUs, 384 GiB of memory and 0 GB of storage. The pricing starts at 0.395 USD per hour.
48 vCPU
384 GiB Memory
Spare SCore
87,194
(All-cores)
1,811
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
1765217
Name
c4a-highmem-48
Description
48 vCPUs, 384 GB RAM
Family
c4a
Hw Virt
Average Time To Start
17
Status
active
Observed At
2026-10-25T09:08:14.051486

Availability

REGION / IDSPOTONDEMAND
Columbus (US) / us-east5
0.6357 USD/h 2.8291 USD/h
Council Bluffs (US) / us-central1
1.472 USD/h 2.8291 USD/h
The Dalles (US) / us-west1
1.472 USD/h 2.8291 USD/h
Moncks Corner (US) / us-east1
1.472 USD/h 2.8291 USD/h
Ashburn (US) / us-east4
1.6852 USD/h 2.8291 USD/h
Mumbai (IN) / asia-south1
1.1297 USD/h 2.9421 USD/h
Eemshaven (NL) / europe-west4
0.395 USD/h 2.9706 USD/h
Stockholm (SE) / europe-north2
1.4519 USD/h 2.9706 USD/h
Queretaro (MX) / northamerica-south1
0.8412 USD/h 3.0838 USD/h
Hamina (FI) / europe-north1
0.7626 USD/h 3.1151 USD/h
Toronto (CA) / northamerica-northeast2
1.2998 USD/h 3.1151 USD/h
St. Ghislain (BE) / europe-west1
1.3275 USD/h 3.1151 USD/h
Montréal (CA) / northamerica-northeast1
1.5061 USD/h 3.1151 USD/h
Johannesburg (ZA) / africa-south1
1.4779 USD/h 3.1152 USD/h
Las Vegas (US) / us-west4
1.6191 USD/h 3.1864 USD/h
London (GB) / europe-west2
1.505 USD/h 3.225 USD/h
Changhua County (TW) / asia-east1
1.0809 USD/h 3.2758 USD/h
Frankfurt (DE) / europe-west3
1.297 USD/h 3.3384 USD/h
Dallas (US) / us-south1
1.2992 USD/h 3.3384 USD/h
Madrid (ES) / europe-southwest1
1.5615 USD/h 3.3384 USD/h
Los Angeles (US) / us-west2
1.2932 USD/h 3.4009 USD/h
Warsaw (PL) / europe-central2
0.89 USD/h 3.4232 USD/h
Doha (QA) / me-central1
1.3728 USD/h 3.4374 USD/h
Jurong West (SG) / asia-southeast1
2.094 USD/h 3.4903 USD/h
Sydney (AU) / australia-southeast1
0.7429 USD/h 3.5368 USD/h
Tokyo (JP) / asia-northeast1
1.7165 USD/h 3.6332 USD/h
Melbourne (AU) / australia-southeast2
0.7725 USD/h 3.6768 USD/h
Zurich (CH) / europe-west6
1.5806 USD/h 3.7062 USD/h
Jakarta (ID) / asia-southeast2
1.5194 USD/h 3.8043 USD/h
Santiago (CL) / southamerica-west1
1.6884 USD/h 4.0455 USD/h
Osasco (BR) / southamerica-east1
1.7942 USD/h 4.4924 USD/h

Processor

vCPUs
48
CPU Allocation
Dedicated
CPU Cores
48
CPU Speed
3 GHz
CPU Architecture
arm64
CPU Family
ARMv8
CPU Model
Neoverse-V2
CPU L1D Cache
64 KiB
CPU L1D Cache Total
3 MiB
CPU L1I Cache
64 KiB
CPU L1I Cache Total
3 MiB
CPU L2 Cache
2 MiB
CPU L2 Cache Total
96 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
48.1
Scalability
100.21

System Resources and Accelerators

MEMORY
Memory Amount
384 GiB
Memory Amount Actual
384 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

      An arm64-based virtual machine featuring dedicated physical cores and high memory density for demanding database and multi-threaded workloads.

      Memory OptimizedGeneral Purpose

      Google Cloud Platform c4a-highmem-48 is an arm64 server instance featuring 48 dedicated physical cores on the ARMv8 Neoverse-V2 architecture running at 3.0 GHz. It is equipped with 384.0 GB of RAM, yielding a high memory-to-core ratio of 8.0 GB per core, though it lacks local storage and GPU accelerators. Benchmarks indicate top-tier capabilities in multi-core processing, database operations, and memory bandwidth, with a Geekbench multi-core score of 25168.0 and a Passmark database operations score of 50138.12. The dedicated core design ensures predictable performance, making it highly cost-efficient for memory-intensive workloads. This instance is best suited for database hosting, software compilation, high-throughput web serving, and memory-bound enterprise applications.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      3.4Score
      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) 8,881,970 ops/sec 1,919,289 ops/sec 4.7 50.00% 50.00% +120.00%
      Redis RPS (pipeline=16, SET) 59,076,055 ops/sec 11,728,058 ops/sec 4.9 20.00% 20.00% +37.00%
      PassMark Memory Mark (composite) 3,290 2,416 1.4 10.00% 10.00% +3.40%
      Memory bandwidth (read, 16 MB ~ L3) 393,449 MB/sec 108,466 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: 1,958

      Geekbench Multi-Core

      Score: 25,168

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 39,762
      Compression
      		 339,793
      Encryption
      		 10,068
      Extended Instructions
      		 62,459
      Floating Point Maths
      		 309,326
      Integer Maths
      		 267,818
      Physics
      		 14,445
      Prime Numbers
      		 652
      Single Threaded
      		 2,077
      String Sorting
      		 236,104

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 3,290
      Database Operations
      		 50,138
      Memory Latency
      		 50
      Memory Read Cached
      		 22,321
      Memory Read Uncached
      		 18,067
      Memory Write
      		 22,758

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 243.34 134.99 0.55×
      bitops
      		 154,911 7,415,232 47.87×
      branch
      		 242,922 11,620,070 47.83×
      funccall
      		 2,111 101,019 47.85×
      funcret
      		 36,931 1,771,488 47.97×
      hash
      		 166,586 7,977,510 47.89×
      intmath
      		 34,981 1,674,107 47.86×
      nop
      		 492,791 23,517,843 47.72×
      prime
      		 531,027 25,418,266 47.87×
      rotate
      		 142,477 6,857,548 48.13×
      str
      		 828,816 39,727,243 47.93×
      wcs
      		 219,149 10,399,870 47.46×
      CryptographySingleMultiScaling
      crypt
      		 3,707 177,574 47.91×
      CompressionSingleMultiScaling
      jpeg
      		 795.04 31,327 39.40×
      zlib
      		 42.35 2,124 50.16×
      HypervisorSingleMultiScaling
      clock
      		 41,708 311,035 7.46×
      clone
      		 477.09 6,683 14.01×
      context
      		 2,652 129,541 48.84×
      cpu-sched
      		 64.77 3,144 48.55×
      eventfd
      		 112,314 1,950,642 17.37×
      fault
      		 21,964 344,502 15.68×
      fork
      		 5,287 114,488 21.66×
      getrandom
      		 66,003 3,161,452 47.90×
      hrtimers
      		 270,746 6,498,564 24.00×
      mprotect
      		 985,372 16,495,861 16.74×
      mtx
      		 8,521,110 2,245,806,675 263.56×
      munmap
      		 3,829 105,448 27.54×
      null
      		 456,262 22,149,238 48.55×
      pipe
      		 1,088,641 26,881,978 24.69×
      priv-instr
      		 816,146 9,113,635 11.17×
      resched
      		 2,643,495 4,914,188 1.86×
      switch
      		 192,096 24,352,774 126.77×
      timermix
      		 559,819 26,691,771 47.68×
      tlb-shootdown
      		 15,173 295,149 19.45×
      vdso
      		 43,203,898 2,065,604,813 47.81×
      vfork
      		 40,938 298,932 7.30×
      yield
      		 61,293,099 66,263,022 1.08×
      zero
      		 2,590,188 124,917,885 48.23×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 2,074 99,359 47.91×
      expmath
      		 392.52 18,791 47.87×
      fma
      		 830,251 39,738,724 47.86×
      fp
      		 163.2 7,863 48.18×
      fractal
      		 8.4 392.69 46.75×
      hyperbolic
      		 379.03 18,136 47.85×
      logmath
      		 459.58 22,012 47.90×
      matrix
      		 7,088 339,548 47.91×
      matrix-3d
      		 1,505 18,550 12.33×
      monte-carlo
      		 204.65 9,957 48.65×
      mpfr
      		 1,541 73,808 47.91×
      powmath
      		 266.49 12,766 47.90×
      trig
      		 509.67 24,406 47.89×
      veccmp
      		 23,349 1,118,567 47.91×
      vecfp
      		 1,327 63,618 47.94×
      vecmath
      		 4,757 227,909 47.91×
      vecshuf
      		 940.75 45,297 48.15×
      vecwide
      		 27,174 1,301,351 47.89×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 9.6 461.39 48.06×
      bsearch
      		 363.33 17,456 48.04×
      bubblesort
      		 1.2 57.6 48.00×
      fibsearch
      		 391.18 18,729 47.88×
      heapsort
      		 14 665.78 47.56×
      hsearch
      		 9,023 436,246 48.35×
      insertionsort
      		 6.8 339.4 49.91×
      malloc
      		 3,496,704 92,241,620 26.38×
      mcontend
      		 212.13 108,643 512.15×
      mergesort
      		 35.8 1,715 47.89×
      qsort
      		 24 1,151 47.97×
      skiplist
      		 7,282 348,250 47.83×
      tree
      		 1.4 47.89 34.21×
      MemorySingleMultiScaling
      cache
      		 435,993 1,332,320 3.06×
      cachehammer
      		 1,987,037 36,479,364 18.36×
      cacheline
      		 38.17 4,344 113.82×
      l1cache
      		 351.71 16,685 47.44×
      memcpy
      		 766.43 36,647 47.82×
      memrate
      		 5.51 52.87 9.60×
      memthrash
      		 208.54 692.19 3.32×
      ptr-chase
      		 15,879,819 421,159,307 26.52×
      spinmem
      		 4,247 39,693 9.35×
      stream
      		 56.97 36,582 642.12×
      vm
      		 126,448 3,090,191 24.44×

      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-48 FAQs