c4-highmem-48 by Google Cloud Platform

c4-highmem-48 is a 48 vCPUs, 372 GB RAM server offered by Google Cloud Platform with 48 vCPUs, 372 GiB of memory and 0 GB of storage. The pricing starts at 0.4783 USD per hour.
48 vCPU
372 GiB Memory
Spare SCore
43,998
(All-cores)
2,052
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
1761048
Name
c4-highmem-48
Description
48 vCPUs, 372 GB RAM
Family
c4
Hw Virt
Average Time To Start
26.5
Status
active
Observed At
2026-10-24T09:00:39.554433

Availability

REGION / IDSPOTONDEMAND
Columbus (US) / us-east5
1.8634 USD/h 3.1281 USD/h
Ashburn (US) / us-east4
1.8676 USD/h 3.1281 USD/h
Council Bluffs (US) / us-central1
1.8723 USD/h 3.1281 USD/h
The Dalles (US) / us-west1
1.8723 USD/h 3.1281 USD/h
Moncks Corner (US) / us-east1
1.8723 USD/h 3.1281 USD/h
Mumbai (IN) / asia-south1
1.0737 USD/h 3.2533 USD/h
Delhi (IN) / asia-south2
1.3526 USD/h 3.2534 USD/h
Bangkok (TH) / asia-southeast3
0.9825 USD/h 3.2845 USD/h
Stockholm (SE) / europe-north2
1.1168 USD/h 3.2845 USD/h
Eemshaven (NL) / europe-west4
1.4337 USD/h 3.2845 USD/h
Queretaro (MX) / northamerica-south1
1.1105 USD/h 3.4097 USD/h
Tel Aviv (IL) / me-west1
0.5675 USD/h 3.4409 USD/h
Montréal (CA) / northamerica-northeast1
0.4783 USD/h 3.4444 USD/h
Hamina (FI) / europe-north1
0.9555 USD/h 3.4444 USD/h
Johannesburg (ZA) / africa-south1
1.1024 USD/h 3.4444 USD/h
St. Ghislain (BE) / europe-west1
1.2402 USD/h 3.4444 USD/h
Toronto (CA) / northamerica-northeast2
1.274 USD/h 3.4444 USD/h
Las Vegas (US) / us-west4
1.1979 USD/h 3.5232 USD/h
London (GB) / europe-west2
1.6413 USD/h 3.5661 USD/h
Changhua County (TW) / asia-east1
2.1732 USD/h 3.6221 USD/h
Paris (FR) / europe-west9
0.5886 USD/h 3.6286 USD/h
Milan (IT) / europe-west8
1.0521 USD/h 3.6286 USD/h
Berlin (DE) / europe-west10
1.6522 USD/h 3.691 USD/h
Dallas (US) / us-south1
0.9836 USD/h 3.6912 USD/h
Madrid (ES) / europe-southwest1
1.1218 USD/h 3.6912 USD/h
Frankfurt (DE) / europe-west3
1.6658 USD/h 3.6912 USD/h
Los Angeles (US) / us-west2
1.1329 USD/h 3.7603 USD/h
Salt Lake City (US) / us-west3
1.1697 USD/h 3.7603 USD/h
Warsaw (PL) / europe-central2
0.9084 USD/h 3.7848 USD/h
Doha (QA) / me-central1
1.0264 USD/h 3.8007 USD/h
Jurong West (SG) / asia-southeast1
1.8621 USD/h 3.8592 USD/h
Sydney (AU) / australia-southeast1
1.2512 USD/h 3.9102 USD/h
Osaka (JP) / asia-northeast2
1.8229 USD/h 4.0172 USD/h
Seoul (KR) / asia-northeast3
1.8812 USD/h 4.0172 USD/h
Tokyo (JP) / asia-northeast1
2.4039 USD/h 4.0172 USD/h
Turin (IT) / europe-west12
0.7898 USD/h 4.0353 USD/h
Melbourne (AU) / australia-southeast2
1.5292 USD/h 4.0666 USD/h
Zurich (CH) / europe-west6
2.3122 USD/h 4.0981 USD/h
Jakarta (ID) / asia-southeast2
0.786 USD/h 4.2064 USD/h
Hong Kong / asia-east2
1.8241 USD/h 4.3759 USD/h
Santiago (CL) / southamerica-west1
1.476 USD/h 4.4732 USD/h
Osasco (BR) / southamerica-east1
1.8267 USD/h 4.9672 USD/h
Dammam (SA) / me-central2
0.7104 USD/h 5.005 USD/h

Processor

vCPUs
48
CPU Allocation
Dedicated
CPU Cores
24
CPU Speed
2.3 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU Model
8581C
CPU L1D Cache
48 KiB
CPU L1D Cache Total
1 MiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
768 KiB
CPU L2 Cache
2 MiB
CPU L2 Cache Total
48 MiB
CPU L3 Cache
260 MiB
CPU L3 Cache Total
260 MiB
CPU Flags
fpu, vme, de, pse, tsc, msr, pae, mce, cx8, apic, sep, mtrr, pge, mca, cmov, pat, pse36, clflush, mmx, fxsr, sse, sse2, ss, ht, syscall, nx, pdpe1gb, rdtscp, lm, constant_tsc, rep_good, nopl, xtopology, nonstop_tsc, cpuid, tsc_known_freq, pni, pclmulqdq, monitor, ssse3, fma, cx16, pcid, sse4_1, sse4_2, x2apic, movbe, popcnt, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, abm, 3dnowprefetch, ssbd, ibrs, ibpb, stibp, ibrs_enhanced, fsgsbase, tsc_adjust, bmi1, hle, avx2, smep, bmi2, erms, invpcid, rtm, avx512f, avx512dq, rdseed, adx, smap, avx512ifma, clflushopt, clwb, avx512cd, sha_ni, avx512bw, avx512vl, xsaveopt, xsavec, xgetbv1, xsaves, avx_vnni, avx512_bf16, wbnoinvd, arat, avx512vbmi, umip, avx512_vbmi2, gfni, vaes, vpclmulqdq, avx512_vnni, avx512_bitalg, avx512_vpopcntdq, la57, rdpid, cldemote, movdiri, movdir64b, fsrm, md_clear, serialize, tsxldtrk, amx_bf16, avx512_fp16, amx_tile, amx_int8, arch_capabilities
Ecpus
21.4
Scalability
44.58

System Resources and Accelerators

MEMORY
Memory Amount
372 GiB
Memory Amount Actual
372 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 memory-optimized, x86_64 server featuring 48 dedicated vCPUs and 372 GB RAM, optimized for database operations and CPU-based inference.

      Memory OptimizedGeneral Purpose

      Google Cloud Platform c4-highmem-48 is a memory-optimized server instance featuring 48 dedicated vCPUs and 372 GB of RAM, powered by an Intel Xeon 8581C processor at 2.3 GHz. Built on the x86_64 architecture, it provides 24 physical cores and a 260 MB L3 cache. The instance lacks local storage and GPU accelerators but includes Intel Advanced Matrix Extensions (AMX) and AVX-512. Benchmarks reveal top-tier performance in image and text processing, alongside strong results in software compilation, database operations, and small-model LLM inference. However, text generation for large 70B models is weak due to the absence of a GPU. This instance is highly efficient for memory-intensive workloads, database hosting, and CPU-based machine learning inference.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      2.9Score
      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) 8,747,475 ops/sec 1,919,289 ops/sec 4.6 50.00% 50.00% +110.00%
      Redis RPS (pipeline=16, SET) 41,227,253 ops/sec 11,728,058 ops/sec 3.4 20.00% 20.00% +28.00%
      PassMark Memory Mark (composite) 2,314 2,416 0.96 10.00% 10.00% -0.41%
      Memory bandwidth (read, 16 MB ~ L3) 179,368 MB/sec 108,466 MB/sec 1.6 10.00% 10.00% +4.80%
      PassMark single-thread CPU 2,702 Mops/s 2,365 Mops/s 1.1 10.00% 10.00% +0.96%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 2,208

      Geekbench Multi-Core

      Score: 17,983

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 57,594
      Compression
      		 768,765
      Encryption
      		 46,227
      Extended Instructions
      		 57,210
      Floating Point Maths
      		 148,477
      Integer Maths
      		 208,402
      Physics
      		 6,955
      Prime Numbers
      		 424
      Single Threaded
      		 2,702
      String Sorting
      		 104,122

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2,314
      Database Operations
      		 22,234
      Memory Latency
      		 58
      Memory Read Cached
      		 24,022
      Memory Read Uncached
      		 7,877
      Memory Write
      		 7,489

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 253.97 164.84 0.65×
      bitops
      		 157,039 3,758,458 23.93×
      branch
      		 147,922 4,523,872 30.58×
      funccall
      		 747.73 20,220 27.04×
      funcret
      		 12,325 412,577 33.47×
      hash
      		 176,018 5,404,785 30.71×
      intmath
      		 63,706 1,595,879 25.05×
      nop
      		 268,078 4,425,664 16.51×
      prime
      		 469,532 12,053,761 25.67×
      rotate
      		 101,752 2,216,060 21.78×
      str
      		 872,472 29,511,690 33.83×
      wcs
      		 670,867 17,587,843 26.22×
      CryptographySingleMultiScaling
      crypt
      		 3,633 82,222 22.63×
      CompressionSingleMultiScaling
      jpeg
      		 846.47 23,126 27.32×
      zlib
      		 52.2 2,019 38.69×
      HypervisorSingleMultiScaling
      clock
      		 35,757 466,700 13.05×
      clone
      		 489.91 6,989 14.27×
      context
      		 5,448 180,583 33.15×
      cpu-sched
      		 67.02 3,014 44.96×
      eventfd
      		 174,553 2,356,315 13.50×
      fault
      		 33,028 324,195 9.82×
      fork
      		 5,071 134,715 26.57×
      getrandom
      		 59,405 1,811,726 30.50×
      hrtimers
      		 148,666 5,747,386 38.66×
      mprotect
      		 1,227,282 13,912,589 11.34×
      mtx
      		 11,963,343 1,069,160,402 89.37×
      munmap
      		 4,096 111,552 27.24×
      null
      		 907,508 29,697,901 32.72×
      pipe
      		 852,544 40,753,388 47.80×
      priv-instr
      		 830,743 18,683,328 22.49×
      resched
      		 15,902,897 7,226,756 0.45×
      switch
      		 778,811 14,320,931 18.39×
      timermix
      		 205,338 7,651,721 37.26×
      tlb-shootdown
      		 16,348 103,191 6.31×
      tsc
      		 585,053 20,353,016 34.79×
      usersyscall
      		 739,864 18,381,590 24.84×
      vdso
      		 92,533,567 2,938,770,799 31.76×
      vfork
      		 38,784 289,132 7.45×
      x86syscall
      		 10,247,151 352,204,045 34.37×
      yield
      		 53,406,403 55,737,607 1.04×
      zero
      		 6,598,380 216,378,433 32.79×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 17,835 458,633 25.71×
      expmath
      		 3,895 107,775 27.67×
      fma
      		 1,372,260 35,604,209 25.95×
      fp
      		 206.4 6,371 30.87×
      fractal
      		 6.4 195.64 30.57×
      hyperbolic
      		 4,001 122,702 30.67×
      logmath
      		 5,176 172,289 33.28×
      matrix
      		 4,879 129,129 26.46×
      matrix-3d
      		 855.85 5,942 6.94×
      monte-carlo
      		 300.56 9,955 33.12×
      mpfr
      		 1,748 42,280 24.19×
      powmath
      		 1,941 62,711 32.31×
      trig
      		 2,725 73,859 27.10×
      veccmp
      		 25,515 607,325 23.80×
      vecfp
      		 1,575 40,236 25.55×
      vecmath
      		 4,032 115,374 28.61×
      vecshuf
      		 846.24 19,765 23.36×
      vecwide
      		 34,514 879,317 25.48×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 9.4 220.79 23.49×
      bsearch
      		 303.48 8,094 26.67×
      bubblesort
      		 1 28.8 28.80×
      fibsearch
      		 344.36 8,385 24.35×
      heapsort
      		 10.2 287.59 28.20×
      hsearch
      		 8,138 216,873 26.65×
      insertionsort
      		 13 240.6 18.51×
      malloc
      		 2,918,280 68,748,481 23.56×
      mcontend
      		 103.86 8,207 79.02×
      mergesort
      		 30.4 916.38 30.14×
      qsort
      		 22.6 649.19 28.73×
      skiplist
      		 5,554 180,562 32.51×
      tree
      		 1.8 39.95 22.19×
      MemorySingleMultiScaling
      cache
      		 240,262 2,736,213 11.39×
      cachehammer
      		 232,098 5,646,904 24.33×
      cacheline
      		 43.38 3,379 77.90×
      l1cache
      		 1,128 8,563 7.59×
      memcpy
      		 437.7 8,979 20.51×
      memrate
      		 0.13 5.39 41.46×
      memthrash
      		 295.55 1,122 3.80×
      ptr-chase
      		 32,912,705 419,842,081 12.76×
      spinmem
      		 244.59 2,264 9.25×
      stream
      		 5.79 2,297 396.75×
      vm
      		 139,978 299,102 2.14×

      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
      c4-highcpu-2 24 GiB0
      c4-standard-2 27 GiB0
      c4-highmem-2 215 GiB0
      c4-highcpu-4 48 GiB0
      c4-standard-4 415 GiB0
      c4-standard-4-lssd 415 GiB0
      c4-highmem-4 431 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      c4-highmem-48 FAQs