c4-highmem-96 by Google Cloud Platform

c4-highmem-96 is a 96 vCPUs, 744 GB RAM server offered by Google Cloud Platform with 96 vCPUs, 744 GiB of memory and 0 GB of storage. The pricing starts at 0.9567 USD per hour.
96 vCPU
744 GiB Memory
Spare SCore
82,698
(All-cores)
2,098
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
1761096
Name
c4-highmem-96
Description
96 vCPUs, 744 GB RAM
Family
c4
Hw Virt
Average Time To Start
37
Status
active
Observed At
2026-10-23T08:42:30.236240

Availability

REGION / IDSPOTONDEMAND
Columbus (US) / us-east5
3.7269 USD/h 6.2563 USD/h
Ashburn (US) / us-east4
3.7352 USD/h 6.2563 USD/h
Council Bluffs (US) / us-central1
3.7446 USD/h 6.2563 USD/h
The Dalles (US) / us-west1
3.7446 USD/h 6.2563 USD/h
Moncks Corner (US) / us-east1
3.7446 USD/h 6.2563 USD/h
Mumbai (IN) / asia-south1
2.1473 USD/h 6.5065 USD/h
Delhi (IN) / asia-south2
2.7051 USD/h 6.5067 USD/h
Bangkok (TH) / asia-southeast3
1.965 USD/h 6.5689 USD/h
Stockholm (SE) / europe-north2
2.2336 USD/h 6.5691 USD/h
Eemshaven (NL) / europe-west4
2.8674 USD/h 6.5691 USD/h
Queretaro (MX) / northamerica-south1
2.2209 USD/h 6.8193 USD/h
Tel Aviv (IL) / me-west1
1.1351 USD/h 6.8819 USD/h
Montréal (CA) / northamerica-northeast1
0.9567 USD/h 6.8888 USD/h
Hamina (FI) / europe-north1
1.9109 USD/h 6.8888 USD/h
Johannesburg (ZA) / africa-south1
2.2048 USD/h 6.8888 USD/h
St. Ghislain (BE) / europe-west1
2.4804 USD/h 6.8888 USD/h
Toronto (CA) / northamerica-northeast2
2.5479 USD/h 6.8888 USD/h
Las Vegas (US) / us-west4
2.3959 USD/h 7.0464 USD/h
London (GB) / europe-west2
3.2826 USD/h 7.1322 USD/h
Changhua County (TW) / asia-east1
4.3463 USD/h 7.2441 USD/h
Paris (FR) / europe-west9
1.1772 USD/h 7.2573 USD/h
Milan (IT) / europe-west8
2.1042 USD/h 7.2573 USD/h
Berlin (DE) / europe-west10
3.3043 USD/h 7.3821 USD/h
Dallas (US) / us-south1
1.9673 USD/h 7.3824 USD/h
Madrid (ES) / europe-southwest1
2.2436 USD/h 7.3824 USD/h
Frankfurt (DE) / europe-west3
3.3316 USD/h 7.3824 USD/h
Los Angeles (US) / us-west2
2.2657 USD/h 7.5207 USD/h
Salt Lake City (US) / us-west3
2.3393 USD/h 7.5207 USD/h
Warsaw (PL) / europe-central2
1.8169 USD/h 7.5697 USD/h
Doha (QA) / me-central1
2.0528 USD/h 7.6014 USD/h
Jurong West (SG) / asia-southeast1
3.7242 USD/h 7.7184 USD/h
Sydney (AU) / australia-southeast1
2.5024 USD/h 7.8203 USD/h
Osaka (JP) / asia-northeast2
3.6457 USD/h 8.0343 USD/h
Seoul (KR) / asia-northeast3
3.7624 USD/h 8.0343 USD/h
Tokyo (JP) / asia-northeast1
4.8078 USD/h 8.0343 USD/h
Turin (IT) / europe-west12
1.5795 USD/h 8.0706 USD/h
Melbourne (AU) / australia-southeast2
3.0584 USD/h 8.1332 USD/h
Zurich (CH) / europe-west6
4.6243 USD/h 8.1962 USD/h
Jakarta (ID) / asia-southeast2
1.572 USD/h 8.4128 USD/h
Hong Kong / asia-east2
3.6482 USD/h 8.7519 USD/h
Santiago (CL) / southamerica-west1
2.952 USD/h 8.9465 USD/h
Osasco (BR) / southamerica-east1
3.6535 USD/h 9.9343 USD/h
Dammam (SA) / me-central2
1.4209 USD/h 10.01 USD/h

Processor

vCPUs
96
CPU Allocation
Dedicated
CPU Cores
48
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
2 MiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
2 MiB
CPU L2 Cache
2 MiB
CPU L2 Cache Total
96 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
39.4
Scalability
41.04

System Resources and Accelerators

MEMORY
Memory Amount
744 GiB
Memory Amount Actual
744 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 high-density, memory-optimized server featuring ninety-six virtual cores and robust multi-threaded performance for demanding enterprise database workloads.

      Memory OptimizedCompute Optimized

      Google Cloud Platform c4-highmem-96 is an x86_64 memory-optimized server featuring 96 vCPUs and 744 GB of RAM, powered by a 2.3 GHz Intel Xeon 8581C processor with 48 physical cores. It lacks bundled local storage and GPUs. The instance delivers strong multi-core performance, ranking in the top 10% for Geekbench multi-core execution, image processing, and static web serving throughput. Memory bandwidth is highly efficient, with uncached read speeds of 288.74 GB/sec. While single-core performance is moderate, the server's high memory-to-vCPU ratio of 7.75 GB makes it qualitatively cost-effective for memory-intensive enterprise workloads. It is highly suited for database operations, software compilation, and medium-scale LLM inference.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      4.7Score
      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) 15,649,217 ops/sec 1,919,289 ops/sec 8.4 50.00% 50.00% +190.00%
      Redis RPS (pipeline=16, SET) 75,172,630 ops/sec 11,728,058 ops/sec 6.2 20.00% 20.00% +44.00%
      PassMark Memory Mark (composite) 2,245 2,416 0.92 10.00% 10.00% -0.83%
      Memory bandwidth (read, 16 MB ~ L3) 364,597 MB/sec 108,466 MB/sec 3.3 10.00% 10.00% +13.00%
      PassMark single-thread CPU 2,553 Mops/s 2,365 Mops/s 1.1 10.00% 10.00% +0.96%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 2,202

      Geekbench Multi-Core

      Score: 21,073

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 83,409
      Compression
      		 1,425,041
      Encryption
      		 87,292
      Extended Instructions
      		 100,867
      Floating Point Maths
      		 280,009
      Integer Maths
      		 394,948
      Physics
      		 12,636
      Prime Numbers
      		 812
      Single Threaded
      		 2,553
      String Sorting
      		 191,986

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2,245
      Database Operations
      		 30,708
      Memory Latency
      		 59
      Memory Read Cached
      		 22,775
      Memory Read Uncached
      		 7,312
      Memory Write
      		 7,137

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 303.78 118.91 0.39×
      bitops
      		 165,615 7,507,225 45.33×
      branch
      		 156,069 9,046,341 57.96×
      funccall
      		 840.03 41,145 48.98×
      funcret
      		 14,096 822,738 58.37×
      hash
      		 198,254 10,824,050 54.60×
      intmath
      		 72,144 3,169,687 43.94×
      nop
      		 296,931 8,853,030 29.82×
      prime
      		 524,324 23,617,198 45.04×
      rotate
      		 110,320 4,424,373 40.10×
      str
      		 1,012,971 52,027,022 51.36×
      wcs
      		 750,247 33,041,313 44.04×
      CryptographySingleMultiScaling
      crypt
      		 3,782 163,407 43.21×
      CompressionSingleMultiScaling
      jpeg
      		 940.22 44,569 47.40×
      zlib
      		 70.51 3,953 56.06×
      HypervisorSingleMultiScaling
      clock
      		 32,414 406,676 12.55×
      clone
      		 512.76 16,595 32.36×
      context
      		 5,794 359,073 61.97×
      cpu-sched
      		 68.19 6,069 89.00×
      eventfd
      		 179,301 4,359,652 24.31×
      fault
      		 34,700 390,005 11.24×
      fork
      		 5,098 96,009 18.83×
      getrandom
      		 66,028 3,610,785 54.69×
      hrtimers
      		 295,008 8,973,856 30.42×
      mprotect
      		 1,154,757 19,452,102 16.85×
      mtx
      		 14,337,965 2,118,760,461 147.77×
      munmap
      		 4,317 153,840 35.64×
      null
      		 1,002,861 59,368,518 59.20×
      pipe
      		 881,884 56,806,556 64.42×
      priv-instr
      		 941,603 14,077,613 14.95×
      resched
      		 15,428,677 12,519,328 0.81×
      switch
      		 410,818 26,558,982 64.65×
      timermix
      		 226,790 15,388,983 67.86×
      tlb-shootdown
      		 14,962 160,759 10.74×
      tsc
      		 649,192 40,584,628 62.52×
      usersyscall
      		 791,891 14,040,816 17.73×
      vdso
      		 100,676,784 5,876,724,469 58.37×
      vfork
      		 36,108 260,252 7.21×
      x86syscall
      		 11,131,613 704,117,683 63.25×
      yield
      		 117,761,504 119,172,685 1.01×
      zero
      		 7,229,101 425,791,539 58.90×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 18,055 870,169 48.20×
      expmath
      		 3,927 214,162 54.53×
      fma
      		 1,459,823 71,001,872 48.64×
      fp
      		 241.98 12,776 52.80×
      fractal
      		 7.2 391.12 54.32×
      hyperbolic
      		 4,499 245,100 54.48×
      logmath
      		 5,779 343,923 59.51×
      matrix
      		 5,375 254,547 47.36×
      matrix-3d
      		 924.36 12,500 13.52×
      monte-carlo
      		 322.93 19,817 61.37×
      mpfr
      		 1,953 82,867 42.43×
      powmath
      		 2,183 124,565 57.05×
      trig
      		 2,984 145,515 48.76×
      veccmp
      		 27,913 1,185,770 42.48×
      vecfp
      		 1,716 81,276 47.36×
      vecmath
      		 4,375 230,203 52.62×
      vecshuf
      		 919.32 39,523 42.99×
      vecwide
      		 39,007 1,710,078 43.84×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 9.8 442.39 45.14×
      bsearch
      		 313.36 15,969 50.96×
      bubblesort
      		 1.2 57.6 48.00×
      fibsearch
      		 341.72 16,658 48.75×
      heapsort
      		 11.2 571.79 51.05×
      hsearch
      		 9,066 419,949 46.32×
      insertionsort
      		 14.2 479.59 33.77×
      malloc
      		 3,155,773 115,266,424 36.53×
      mcontend
      		 92.07 15,633 169.79×
      mergesort
      		 34 1,801 52.98×
      qsort
      		 24.6 1,243 50.52×
      skiplist
      		 6,087 360,892 59.29×
      tree
      		 2 79.92 39.96×
      MemorySingleMultiScaling
      cache
      		 218,408 9,980,064 45.69×
      cachehammer
      		 220,434 8,817,751 40.00×
      cacheline
      		 45.18 4,018 88.92×
      l1cache
      		 1,237 16,448 13.29×
      memcpy
      		 494.45 18,080 36.57×
      memrate
      		 0.13 10.22 78.62×
      memthrash
      		 301.95 2,020 6.69×
      ptr-chase
      		 35,281,097 840,910,286 23.83×
      spinmem
      		 255.59 4,512 17.65×
      stream
      		 2.89 4,544 1572.39×
      vm
      		 169,195 306,463 1.81×

      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
      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-96 FAQs