c4-highmem-32 by Google Cloud Platform

c4-highmem-32 is a 32 vCPUs, 248 GB RAM server offered by Google Cloud Platform with 32 vCPUs, 248 GiB of memory and 0 GB of storage. The pricing starts at 0.3415 USD per hour.
32 vCPU
248 GiB Memory
Spare SCore
31,499
(All-cores)
2,117
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
1761032
Name
c4-highmem-32
Description
32 vCPUs, 248 GB RAM
Family
c4
Hw Virt
Average Time To Start
29
Status
active
Observed At
2026-11-06T09:26:41.535601

Availability

REGION / IDSPOTONDEMAND
Columbus (US) / us-east5
1.2423 USD/h 2.0854 USD/h
Ashburn (US) / us-east4
1.2451 USD/h 2.0854 USD/h
Council Bluffs (US) / us-central1
1.2482 USD/h 2.0854 USD/h
The Dalles (US) / us-west1
1.2482 USD/h 2.0854 USD/h
Moncks Corner (US) / us-east1
1.2482 USD/h 2.0854 USD/h
Mumbai (IN) / asia-south1
0.7158 USD/h 2.1688 USD/h
Delhi (IN) / asia-south2
0.8138 USD/h 2.1689 USD/h
Bangkok (TH) / asia-southeast3
0.5911 USD/h 2.1896 USD/h
Stockholm (SE) / europe-north2
0.7445 USD/h 2.1897 USD/h
Eemshaven (NL) / europe-west4
0.9533 USD/h 2.1897 USD/h
Queretaro (MX) / northamerica-south1
0.6682 USD/h 2.2731 USD/h
Tel Aviv (IL) / me-west1
0.3415 USD/h 2.294 USD/h
Montréal (CA) / northamerica-northeast1
0.3857 USD/h 2.2963 USD/h
Hamina (FI) / europe-north1
0.575 USD/h 2.2963 USD/h
Johannesburg (ZA) / africa-south1
0.7349 USD/h 2.2963 USD/h
St. Ghislain (BE) / europe-west1
0.8268 USD/h 2.2963 USD/h
Toronto (CA) / northamerica-northeast2
0.8493 USD/h 2.2963 USD/h
Las Vegas (US) / us-west4
0.7986 USD/h 2.3488 USD/h
London (GB) / europe-west2
1.0917 USD/h 2.3774 USD/h
Changhua County (TW) / asia-east1
1.4488 USD/h 2.4147 USD/h
Paris (FR) / europe-west9
0.3541 USD/h 2.4191 USD/h
Milan (IT) / europe-west8
0.7014 USD/h 2.4191 USD/h
Berlin (DE) / europe-west10
1.1014 USD/h 2.4607 USD/h
Dallas (US) / us-south1
0.5918 USD/h 2.4608 USD/h
Madrid (ES) / europe-southwest1
0.6749 USD/h 2.4608 USD/h
Frankfurt (DE) / europe-west3
1.1077 USD/h 2.4608 USD/h
Salt Lake City (US) / us-west3
0.8147 USD/h 2.5069 USD/h
Los Angeles (US) / us-west2
0.8721 USD/h 2.5069 USD/h
Warsaw (PL) / europe-central2
0.6056 USD/h 2.5232 USD/h
Doha (QA) / me-central1
0.6843 USD/h 2.5338 USD/h
Jurong West (SG) / asia-southeast1
1.2383 USD/h 2.5728 USD/h
Sydney (AU) / australia-southeast1
0.8341 USD/h 2.6068 USD/h
Osaka (JP) / asia-northeast2
1.0966 USD/h 2.6781 USD/h
Seoul (KR) / asia-northeast3
1.1319 USD/h 2.6781 USD/h
Tokyo (JP) / asia-northeast1
1.6026 USD/h 2.6781 USD/h
Turin (IT) / europe-west12
0.4749 USD/h 2.6902 USD/h
Melbourne (AU) / australia-southeast2
0.92 USD/h 2.7111 USD/h
Zurich (CH) / europe-west6
1.6389 USD/h 2.7321 USD/h
Jakarta (ID) / asia-southeast2
0.473 USD/h 2.8043 USD/h
Hong Kong / asia-east2
1.0975 USD/h 2.9173 USD/h
Santiago (CL) / southamerica-west1
0.984 USD/h 2.9822 USD/h
Osasco (BR) / southamerica-east1
1.2725 USD/h 3.3114 USD/h
Dammam (SA) / me-central2
0.4951 USD/h 3.3367 USD/h

Processor

vCPUs
32
CPU Allocation
Dedicated
CPU Cores
16
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
768 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
512 KiB
CPU L2 Cache
2 MiB
CPU L2 Cache Total
32 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
14.9
Scalability
46.56

System Resources and Accelerators

MEMORY
Memory Amount
248 GiB
Memory Amount Actual
248 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 dedicated Intel Xeon processors and advanced matrix extensions for high-throughput memory and web-serving workloads.

      Memory OptimizedGeneral Purpose

      Google Cloud Platform c4-highmem-32 is a memory-optimized server instance powered by an Intel Xeon 8581C x86_64 processor with 32 dedicated vCPUs and 248.0 GB of RAM. It features a 260 MB L3 cache and advanced instruction sets including Intel AMX and AVX-512. The instance does not include local storage or GPUs. Benchmark results show strong performance in static web serving at 51.15 GB/sec, image processing, and small-model LLM text generation, which reaches 421.19 tokens/sec. However, it exhibits poor performance on larger 70B LLM text generation tasks. This configuration is qualitatively cost-effective for memory-intensive workloads that do not require local NVMe storage or GPU acceleration, making it appropriate for database operations, software compilation, and memory-cached web serving.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      2.2Score
      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) 5,823,266 ops/sec 1,936,298 ops/sec 3.1 50.00% 50.00% +76.00%
      Redis RPS (pipeline=16, SET) 27,521,229 ops/sec 11,797,257 ops/sec 2.3 20.00% 20.00% +18.00%
      PassMark Memory Mark (composite) 2,238 2,407 0.92 10.00% 10.00% -0.83%
      Memory bandwidth (read, 16 MB ~ L3) 196,940 MB/sec 108,490 MB/sec 1.8 10.00% 10.00% +6.10%
      PassMark single-thread CPU 3,029 Mops/s 2,365 Mops/s 1.2 10.00% 10.00% +1.80%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,933

      Geekbench Multi-Core

      Score: 15,636

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 47,957
      Compression
      		 566,001
      Encryption
      		 34,227
      Extended Instructions
      		 42,878
      Floating Point Maths
      		 111,697
      Integer Maths
      		 156,546
      Physics
      		 6,271
      Prime Numbers
      		 321
      Single Threaded
      		 3,029
      String Sorting
      		 78,472

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2,238
      Database Operations
      		 16,512
      Memory Latency
      		 63
      Memory Read Cached
      		 26,702
      Memory Read Uncached
      		 7,654
      Memory Write
      		 7,235

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 253.37 187.18 0.74×
      bitops
      		 136,820 2,505,573 18.31×
      branch
      		 129,162 3,015,490 23.35×
      funccall
      		 696.93 13,356 19.16×
      funcret
      		 11,626 274,449 23.61×
      hash
      		 164,259 3,610,370 21.98×
      intmath
      		 59,732 1,044,453 17.49×
      nop
      		 251,215 2,951,085 11.75×
      prime
      		 439,797 8,060,430 18.33×
      rotate
      		 91,539 1,476,339 16.13×
      str
      		 840,593 18,905,374 22.49×
      wcs
      		 629,511 11,756,789 18.68×
      CryptographySingleMultiScaling
      crypt
      		 3,121 54,766 17.55×
      CompressionSingleMultiScaling
      jpeg
      		 757.85 15,071 19.89×
      zlib
      		 51.48 1,344 26.12×
      HypervisorSingleMultiScaling
      clock
      		 36,107 398,006 11.02×
      clone
      		 469.84 5,497 11.70×
      context
      		 4,799 119,633 24.93×
      cpu-sched
      		 63.24 2,015 31.86×
      eventfd
      		 154,836 1,598,482 10.32×
      fault
      		 29,147 320,565 11.00×
      fork
      		 5,157 101,612 19.70×
      getrandom
      		 54,470 1,207,300 22.16×
      hrtimers
      		 232,481 4,022,984 17.30×
      mprotect
      		 1,119,224 9,664,724 8.64×
      mtx
      		 12,151,449 942,650,193 77.58×
      munmap
      		 4,140 78,930 19.07×
      null
      		 834,602 19,813,897 23.74×
      pipe
      		 831,313 24,614,493 29.61×
      priv-instr
      		 770,308 15,393,036 19.98×
      resched
      		 13,184,280 3,742,084 0.28×
      switch
      		 783,330 9,557,892 12.20×
      timermix
      		 193,130 5,068,762 26.25×
      tlb-shootdown
      		 12,305 73,710 5.99×
      tsc
      		 537,209 13,532,060 25.19×
      usersyscall
      		 656,739 13,487,122 20.54×
      vdso
      		 83,431,571 1,958,369,525 23.47×
      vfork
      		 38,746 279,364 7.21×
      x86syscall
      		 9,256,129 234,861,766 25.37×
      yield
      		 26,592,211 35,208,592 1.32×
      zero
      		 5,999,011 142,451,238 23.75×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 14,941 294,942 19.74×
      expmath
      		 3,247 71,703 22.08×
      fma
      		 1,205,145 23,738,447 19.70×
      fp
      		 191.8 4,245 22.13×
      fractal
      		 6 130.41 21.73×
      hyperbolic
      		 3,750 81,877 21.83×
      logmath
      		 4,792 114,867 23.97×
      matrix
      		 4,753 86,010 18.10×
      matrix-3d
      		 787.54 5,218 6.63×
      monte-carlo
      		 269.23 6,571 24.40×
      mpfr
      		 1,618 28,182 17.42×
      powmath
      		 1,818 41,665 22.92×
      trig
      		 2,474 49,284 19.92×
      veccmp
      		 23,128 404,791 17.50×
      vecfp
      		 1,415 26,826 18.95×
      vecmath
      		 3,625 76,862 21.21×
      vecshuf
      		 763.04 13,141 17.22×
      vecwide
      		 31,319 589,177 18.81×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 8.2 147.19 17.95×
      bsearch
      		 266.24 5,646 21.20×
      bubblesort
      		 1 19.2 19.20×
      fibsearch
      		 287.83 5,569 19.35×
      heapsort
      		 9.2 188.2 20.46×
      hsearch
      		 7,522 144,247 19.18×
      insertionsort
      		 11.8 160.6 13.61×
      malloc
      		 2,794,274 47,896,365 17.14×
      mcontend
      		 105.86 5,603 52.93×
      mergesort
      		 28.2 610.19 21.64×
      qsort
      		 20.4 432.39 21.20×
      skiplist
      		 5,033 120,461 23.93×
      tree
      		 1.6 31.97 19.98×
      MemorySingleMultiScaling
      cache
      		 256,595 2,015,720 7.86×
      cachehammer
      		 221,949 4,489,537 20.23×
      cacheline
      		 71.51 2,801 39.17×
      l1cache
      		 1,024 5,756 5.62×
      memcpy
      		 409.92 5,978 14.58×
      memrate
      		 0.13 3.71 28.54×
      memthrash
      		 221.64 939.32 4.24×
      ptr-chase
      		 31,735,427 322,590,181 10.16×
      spinmem
      		 236.59 1,402 5.92×
      stream
      		 6.1 1,505 246.78×
      vm
      		 127,843 296,625 2.32×

      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-32 FAQs