n4-highmem-32 by Google Cloud Platform

n4-highmem-32 is a 32 vCPUs, 256 GB RAM server offered by Google Cloud Platform with 32 vCPUs, 256 GiB of memory and 0 GB of storage. The pricing starts at 0.2403 USD per hour.
32 vCPU
256 GiB Memory
Spare SCore
25,675
(All-cores)
1,566
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
1750013
Name
n4-highmem-32
Description
32 vCPUs, 256 GB RAM
Family
n4
Hw Virt
Average Time To Start
20
Status
active
Observed At
2026-11-04T04:31:56.398035

Availability

REGION / IDSPOTONDEMAND
Columbus (US) / us-east5
0.6379 USD/h 1.9043 USD/h
Ashburn (US) / us-east4
0.9669 USD/h 1.9043 USD/h
Council Bluffs (US) / us-central1
1.0701 USD/h 1.9043 USD/h
The Dalles (US) / us-west1
1.0701 USD/h 1.9043 USD/h
Moncks Corner (US) / us-east1
1.0701 USD/h 1.9043 USD/h
Mumbai (IN) / asia-south1
0.4304 USD/h 1.9805 USD/h
Delhi (IN) / asia-south2
0.6342 USD/h 1.9805 USD/h
Eemshaven (NL) / europe-west4
0.4175 USD/h 1.9995 USD/h
Stockholm (SE) / europe-north2
0.8242 USD/h 1.9995 USD/h
Bangkok (TH) / asia-southeast3
0.3786 USD/h 1.9996 USD/h
Queretaro (MX) / northamerica-south1
0.5571 USD/h 2.0757 USD/h
Tel Aviv (IL) / me-west1
0.5489 USD/h 2.0948 USD/h
St. Ghislain (BE) / europe-west1
0.2739 USD/h 2.0968 USD/h
Montréal (CA) / northamerica-northeast1
0.391 USD/h 2.0968 USD/h
Johannesburg (ZA) / africa-south1
0.503 USD/h 2.0968 USD/h
Toronto (CA) / northamerica-northeast2
0.7726 USD/h 2.0968 USD/h
Hamina (FI) / europe-north1
0.8701 USD/h 2.0968 USD/h
Las Vegas (US) / us-west4
0.8954 USD/h 2.1448 USD/h
London (GB) / europe-west2
0.8321 USD/h 2.1709 USD/h
Changhua County (TW) / asia-east1
0.8382 USD/h 2.205 USD/h
Milan (IT) / europe-west8
0.4092 USD/h 2.209 USD/h
Paris (FR) / europe-west9
0.7901 USD/h 2.209 USD/h
Dallas (US) / us-south1
0.3949 USD/h 2.2471 USD/h
Madrid (ES) / europe-southwest1
0.5008 USD/h 2.2471 USD/h
Frankfurt (DE) / europe-west3
1.3384 USD/h 2.2471 USD/h
Salt Lake City (US) / us-west3
0.4875 USD/h 2.2892 USD/h
Los Angeles (US) / us-west2
1.2969 USD/h 2.2892 USD/h
Warsaw (PL) / europe-central2
1.1708 USD/h 2.3042 USD/h
Doha (QA) / me-central1
1.0644 USD/h 2.3137 USD/h
Jurong West (SG) / asia-southeast1
1.409 USD/h 2.3494 USD/h
Sydney (AU) / australia-southeast1
1.1528 USD/h 2.3804 USD/h
Osaka (JP) / asia-northeast2
0.886 USD/h 2.4455 USD/h
Seoul (KR) / asia-northeast3
1.1546 USD/h 2.4455 USD/h
Tokyo (JP) / asia-northeast1
1.3904 USD/h 2.4455 USD/h
Melbourne (AU) / australia-southeast2
0.8722 USD/h 2.4756 USD/h
Zurich (CH) / europe-west6
1.2675 USD/h 2.4947 USD/h
Jakarta (ID) / asia-southeast2
0.7424 USD/h 2.5607 USD/h
Hong Kong / asia-east2
0.2403 USD/h 2.664 USD/h
Santiago (CL) / southamerica-west1
0.5044 USD/h 2.7232 USD/h
Osasco (BR) / southamerica-east1
0.3992 USD/h 3.0239 USD/h
Dammam (SA) / me-central2
0.5523 USD/h 3.0469 USD/h

Processor

vCPUs
32
CPU Allocation
Dedicated
CPU Cores
16
CPU Architecture
x86_64
CPU Manufacturer
Intel
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, smx, est, ssse3, sdbg, fma, cx16, xtpr, pdcm, pcid, dca, sse4_1, sse4_2, x2apic, movbe, popcnt, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, abm, 3dnowprefetch, cat_l3, cat_l2, cdp_l3, cdp_l2, ssbd, mba, 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, cqm_llc, cqm_occup_llc, cqm_mbm_total, cqm_mbm_local, 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
16.4
Scalability
51.25

System Resources and Accelerators

MEMORY
Memory Amount
256 GiB
Memory Amount Actual
256 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 x86_64 server featuring a 1:8 vCPU-to-RAM ratio, strong memory bandwidth, and Intel Advanced Matrix Extensions for memory-intensive workloads.

      Memory OptimizedGeneral Purpose

      Google Cloud Platform n4-highmem-32 is an x86_64 memory-optimized server featuring 32 vCPUs and 256 GB of RAM, establishing an 8 GB per vCPU ratio. Lacking local storage and GPUs, it relies entirely on network-attached storage. The platform demonstrates strong memory performance, with large-block uncached read bandwidth at 208.51 GB/sec and write bandwidth at 99.59 GB/sec, both ranking in the top 25% of benchmarks. It also achieves a strong static web serving throughput of 44.59 GB/sec. Computational metrics, such as a Geekbench multi-core score of 15821.0, fall within the average range. Supported by Intel Advanced Matrix Extensions (AMX) and AVX-512, this instance is designed for memory-intensive workloads, including in-memory databases, caching layers, and data processing tasks that require significant memory capacity relative to compute resources.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      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) 4,750,813 ops/sec 1,933,252 ops/sec 2.5 50.00% 50.00% +58.00%
      Redis RPS (pipeline=16, SET) 24,756,314 ops/sec 11,794,699 ops/sec 2.1 20.00% 20.00% +16.00%
      PassMark Memory Mark (composite) 2,038 2,412 0.83 10.00% 10.00% -1.80%
      Memory bandwidth (read, 16 MB ~ L3) 310,480 MB/sec 108,490 MB/sec 2.8 10.00% 10.00% +11.00%
      PassMark single-thread CPU 2,427 Mops/s 2,365 Mops/s 1 10.00% 10.00% 0.00%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,880

      Geekbench Multi-Core

      Score: 15,821

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 38,514
      Compression
      		 456,055
      Encryption
      		 27,360
      Extended Instructions
      		 34,821
      Floating Point Maths
      		 87,377
      Integer Maths
      		 122,717
      Physics
      		 6,050
      Prime Numbers
      		 263
      Single Threaded
      		 2,427
      String Sorting
      		 63,050

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2,038
      Database Operations
      		 15,420
      Memory Latency
      		 72
      Memory Read Cached
      		 21,745
      Memory Read Uncached
      		 7,577
      Memory Write
      		 6,992

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 115.23 88.8 0.77×
      bitops
      		 137,952 2,583,686 18.73×
      branch
      		 128,741 3,367,950 26.16×
      funccall
      		 710.88 15,111 21.26×
      funcret
      		 11,698 294,651 25.19×
      hash
      		 159,162 3,726,395 23.41×
      intmath
      		 59,609 1,204,456 20.21×
      nop
      		 249,571 4,278,583 17.14×
      prime
      		 442,782 9,495,308 21.44×
      rotate
      		 91,009 2,151,577 23.64×
      str
      		 879,776 19,152,236 21.77×
      wcs
      		 629,269 11,923,856 18.95×
      CryptographySingleMultiScaling
      crypt
      		 3,103 63,474 20.46×
      CompressionSingleMultiScaling
      jpeg
      		 756.39 15,557 20.57×
      zlib
      		 61.17 1,437 23.49×
      HypervisorSingleMultiScaling
      clock
      		 37,683 312,815 8.30×
      clone
      		 364.44 3,827 10.50×
      context
      		 4,739 127,099 26.82×
      cpu-sched
      		 68.53 2,074 30.26×
      eventfd
      		 47,125 901,085 19.12×
      fault
      		 25,041 175,961 7.03×
      fork
      		 4,136 66,019 15.96×
      getrandom
      		 53,321 1,272,207 23.86×
      hrtimers
      		 361,974 3,776,763 10.43×
      mprotect
      		 710,125 9,289,846 13.08×
      mtx
      		 31,634,927 1,057,726,344 33.44×
      munmap
      		 2,322 54,437 23.44×
      null
      		 826,002 21,697,653 26.27×
      pipe
      		 487,849 20,262,581 41.53×
      priv-instr
      		 781,547 10,100,098 12.92×
      resched
      		 10,922,674 3,933,259 0.36×
      switch
      		 63,099 11,192,751 177.38×
      timermix
      		 195,343 5,469,975 28.00×
      tlb-shootdown
      		 6,916 48,545 7.02×
      tsc
      		 533,374 14,083,234 26.40×
      usersyscall
      		 669,858 9,591,111 14.32×
      vdso
      		 83,903,895 2,125,584,392 25.33×
      vfork
      		 24,420 167,094 6.84×
      x86syscall
      		 9,226,062 250,947,226 27.20×
      yield
      		 33,589,717 35,508,623 1.06×
      zero
      		 5,949,337 157,426,090 26.46×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 15,174 323,463 21.32×
      expmath
      		 3,222 76,992 23.89×
      fma
      		 1,110,116 24,586,338 22.15×
      fp
      		 194.32 4,539 23.36×
      fractal
      		 6.6 142.83 21.64×
      hyperbolic
      		 3,734 88,693 23.75×
      logmath
      		 4,761 123,030 25.84×
      matrix
      		 4,702 89,247 18.98×
      matrix-3d
      		 428.84 6,741 15.72×
      monte-carlo
      		 269.59 7,234 26.84×
      mpfr
      		 1,609 33,253 20.67×
      powmath
      		 1,809 45,067 24.92×
      trig
      		 2,507 53,231 21.23×
      veccmp
      		 21,853 419,912 19.22×
      vecfp
      		 1,352 28,231 20.87×
      vecmath
      		 3,542 80,907 22.84×
      vecshuf
      		 749.9 13,770 18.36×
      vecwide
      		 26,806 527,452 19.68×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 9 179.19 19.91×
      bsearch
      		 289.4 5,816 20.10×
      bubblesort
      		 1 19.2 19.20×
      fibsearch
      		 274.91 5,313 19.33×
      heapsort
      		 9 199.19 22.13×
      hsearch
      		 7,623 154,581 20.28×
      insertionsort
      		 11.8 185.2 15.69×
      malloc
      		 1,901,362 28,522,576 15.00×
      mcontend
      		 63.1 4,854 76.92×
      mergesort
      		 28.4 659.58 23.22×
      qsort
      		 20.4 455.79 22.34×
      skiplist
      		 5,906 146,399 24.79×
      tree
      		 1.2 25.57 21.31×
      MemorySingleMultiScaling
      cache
      		 261,257 1,956,800 7.49×
      cachehammer
      		 152,122 3,636,986 23.91×
      cacheline
      		 37.77 1,825 48.33×
      l1cache
      		 680.71 5,729 8.42×
      memcpy
      		 626.95 10,518 16.78×
      memrate
      		 0.1 - -
      memthrash
      		 155.58 1,120 7.20×
      ptr-chase
      		 17,801,808 319,832,587 17.97×
      spinmem
      		 218.99 1,522 6.95×
      stream
      		 5.57 3,331 598.08×
      vm
      		 59,617 295,417 4.96×

      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
      n4-highcpu-2 24 GiB0
      n4-standard-2 28 GiB0
      n4-highmem-2 216 GiB0
      n4-highcpu-4 48 GiB0
      n4-standard-4 416 GiB0
      n4-highmem-4 432 GiB0
      n4-highcpu-8 816 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      n4-highmem-32 FAQs