n4-highmem-64 by Google Cloud Platform

n4-highmem-64 is a 64 vCPUs, 512 GB RAM server offered by Google Cloud Platform with 64 vCPUs, 512 GiB of memory and 0 GB of storage. The pricing starts at 0.4805 USD per hour.
64 vCPU
512 GiB Memory
Spare SCore
52,914
(All-cores)
1,699
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
1750015
Name
n4-highmem-64
Description
64 vCPUs, 512 GB RAM
Family
n4
Hw Virt
Average Time To Start
34.5
Status
active
Observed At
2026-10-27T00:57:32.576578

Availability

REGION / IDSPOTONDEMAND
Columbus (US) / us-east5
1.2151 USD/h 3.8086 USD/h
Ashburn (US) / us-east4
2.0356 USD/h 3.8086 USD/h
Council Bluffs (US) / us-central1
2.2529 USD/h 3.8086 USD/h
The Dalles (US) / us-west1
2.2529 USD/h 3.8086 USD/h
Moncks Corner (US) / us-east1
2.2529 USD/h 3.8086 USD/h
Mumbai (IN) / asia-south1
0.8196 USD/h 3.961 USD/h
Delhi (IN) / asia-south2
1.3354 USD/h 3.961 USD/h
Bangkok (TH) / asia-southeast3
0.7973 USD/h 3.9991 USD/h
Eemshaven (NL) / europe-west4
0.8791 USD/h 3.9991 USD/h
Stockholm (SE) / europe-north2
1.7353 USD/h 3.9991 USD/h
Queretaro (MX) / northamerica-south1
1.1725 USD/h 4.1514 USD/h
Tel Aviv (IL) / me-west1
1.1555 USD/h 4.1895 USD/h
St. Ghislain (BE) / europe-west1
0.577 USD/h 4.1937 USD/h
Montréal (CA) / northamerica-northeast1
0.711 USD/h 4.1937 USD/h
Johannesburg (ZA) / africa-south1
1.0061 USD/h 4.1937 USD/h
Toronto (CA) / northamerica-northeast2
1.627 USD/h 4.1937 USD/h
Hamina (FI) / europe-north1
1.8318 USD/h 4.1937 USD/h
Las Vegas (US) / us-west4
1.8851 USD/h 4.2897 USD/h
London (GB) / europe-west2
1.7518 USD/h 4.3418 USD/h
Changhua County (TW) / asia-east1
1.6764 USD/h 4.41 USD/h
Milan (IT) / europe-west8
0.7439 USD/h 4.418 USD/h
Paris (FR) / europe-west9
1.5048 USD/h 4.418 USD/h
Dallas (US) / us-south1
0.8316 USD/h 4.4942 USD/h
Madrid (ES) / europe-southwest1
0.9101 USD/h 4.4942 USD/h
Frankfurt (DE) / europe-west3
2.6767 USD/h 4.4942 USD/h
Salt Lake City (US) / us-west3
1.0264 USD/h 4.5784 USD/h
Los Angeles (US) / us-west2
2.7305 USD/h 4.5784 USD/h
Warsaw (PL) / europe-central2
2.1289 USD/h 4.6085 USD/h
Doha (QA) / me-central1
2.1288 USD/h 4.6275 USD/h
Jurong West (SG) / asia-southeast1
2.8179 USD/h 4.6987 USD/h
Sydney (AU) / australia-southeast1
2.3055 USD/h 4.7608 USD/h
Osaka (JP) / asia-northeast2
1.8651 USD/h 4.8911 USD/h
Seoul (KR) / asia-northeast3
2.431 USD/h 4.8911 USD/h
Tokyo (JP) / asia-northeast1
2.9272 USD/h 4.8911 USD/h
Melbourne (AU) / australia-southeast2
1.6614 USD/h 4.9512 USD/h
Zurich (CH) / europe-west6
2.4143 USD/h 4.9893 USD/h
Jakarta (ID) / asia-southeast2
1.4848 USD/h 5.1215 USD/h
Hong Kong / asia-east2
0.4805 USD/h 5.3279 USD/h
Santiago (CL) / southamerica-west1
1.0621 USD/h 5.4464 USD/h
Osasco (BR) / southamerica-east1
0.8402 USD/h 6.0477 USD/h
Dammam (SA) / me-central2
1.0519 USD/h 6.0938 USD/h

Processor

vCPUs
64
CPU Allocation
Dedicated
CPU Cores
32
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU L1D Cache
48 KiB
CPU L1D Cache Total
2 MiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
1 MiB
CPU L2 Cache
2 MiB
CPU L2 Cache Total
64 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
31.1
Scalability
48.59

System Resources and Accelerators

MEMORY
Memory Amount
512 GiB
Memory Amount Actual
512 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 virtual server with 512 GB RAM and 64 dedicated vCPUs, engineered for high-throughput database and memory-intensive workloads.

      Memory OptimizedGeneral Purpose

      Google Cloud Platform n4-highmem-64 is an x86_64 memory-optimized server featuring 64 dedicated Intel vCPUs and 512 GB of RAM. Lacking local storage and GPU accelerators, this instance relies on its high memory-to-vCPU ratio of 8 GB per core and a 260 MB L3 cache to handle data-dense workloads. Benchmark data highlights strong performance in memory bandwidth, with read-only large-block speeds reaching 276.11 GB/sec, and high multi-core efficiency, reflected in a PassMark CPU score of 62,986.78. The processor supports advanced instruction sets like AVX-512 and Intel AMX, which accelerate mathematical and cryptographic operations. This profile makes the instance highly effective for in-memory databases, Redis deployments, software compilation, and large-scale enterprise applications requiring substantial memory capacity without local disk overhead.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      3.3Score
      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) 9,415,679 ops/sec 1,918,343 ops/sec 4.9 50.00% 50.00% +120.00%
      Redis RPS (pipeline=16, SET) 48,891,942 ops/sec 11,704,734 ops/sec 4.1 20.00% 20.00% +33.00%
      PassMark Memory Mark (composite) 2,149 2,416 0.88 10.00% 10.00% -1.30%
      Memory bandwidth (read, 16 MB ~ L3) 355,678 MB/sec 108,420 MB/sec 3.3 10.00% 10.00% +13.00%
      PassMark single-thread CPU 2,442 Mops/s 2,365 Mops/s 1 10.00% 10.00% 0.00%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,807

      Geekbench Multi-Core

      Score: 17,904

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 62,987
      Compression
      		 932,628
      Encryption
      		 54,355
      Extended Instructions
      		 67,619
      Floating Point Maths
      		 173,715
      Integer Maths
      		 242,754
      Physics
      		 10,872
      Prime Numbers
      		 520
      Single Threaded
      		 2,442
      String Sorting
      		 123,365

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2,149
      Database Operations
      		 29,376
      Memory Latency
      		 69
      Memory Read Cached
      		 21,784
      Memory Read Uncached
      		 7,975
      Memory Write
      		 7,629

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 219.11 132.69 0.61×
      bitops
      		 122,267 4,657,675 38.09×
      branch
      		 114,370 5,600,486 48.97×
      funccall
      		 613.93 25,112 40.90×
      funcret
      		 10,105 509,479 50.42×
      hash
      		 142,971 6,692,484 46.81×
      intmath
      		 52,433 2,085,109 39.77×
      nop
      		 218,424 5,690,732 26.05×
      prime
      		 393,158 15,038,574 38.25×
      rotate
      		 81,056 2,754,702 33.99×
      str
      		 742,210 36,162,966 48.72×
      wcs
      		 561,253 21,518,633 38.34×
      CryptographySingleMultiScaling
      crypt
      		 2,757 101,957 36.98×
      CompressionSingleMultiScaling
      jpeg
      		 666.04 27,754 41.67×
      zlib
      		 60.73 2,594 42.72×
      HypervisorSingleMultiScaling
      clock
      		 33,026 428,594 12.98×
      clone
      		 418.97 8,816 21.04×
      context
      		 4,238 222,505 52.50×
      cpu-sched
      		 67 4,138 61.76×
      eventfd
      		 54,520 1,842,011 33.79×
      fault
      		 21,095 267,584 12.68×
      fork
      		 4,377 104,002 23.76×
      getrandom
      		 48,053 2,235,021 46.51×
      hrtimers
      		 135,328 5,709,693 42.19×
      mprotect
      		 989,163 15,294,291 15.46×
      mtx
      		 12,453,131 1,806,629,503 145.07×
      munmap
      		 3,087 100,282 32.49×
      null
      		 735,995 36,634,285 49.78×
      pipe
      		 631,179 36,255,232 57.44×
      priv-instr
      		 689,338 14,694,720 21.32×
      resched
      		 14,382,003 6,730,161 0.47×
      switch
      		 77,411 16,485,115 212.96×
      timermix
      		 196,176 10,407,572 53.05×
      tlb-shootdown
      		 10,334 116,481 11.27×
      tsc
      		 476,477 25,162,711 52.81×
      usersyscall
      		 568,692 14,663,614 25.78×
      vdso
      		 73,875,455 3,619,493,569 48.99×
      vfork
      		 27,093 245,680 9.07×
      x86syscall
      		 8,198,368 435,264,301 53.09×
      yield
      		 52,928,757 67,033,907 1.27×
      zero
      		 5,341,978 266,467,071 49.88×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 13,130 548,870 41.80×
      expmath
      		 2,890 132,705 45.92×
      fma
      		 1,070,386 44,136,971 41.23×
      fp
      		 177.6 7,848 44.19×
      fractal
      		 5.4 242.11 44.84×
      hyperbolic
      		 3,362 151,803 45.15×
      logmath
      		 4,239 213,305 50.32×
      matrix
      		 4,209 156,432 37.17×
      matrix-3d
      		 665.92 10,069 15.12×
      monte-carlo
      		 237.11 12,345 52.06×
      mpfr
      		 1,442 52,687 36.55×
      powmath
      		 1,604 77,198 48.12×
      trig
      		 2,211 91,283 41.29×
      veccmp
      		 20,337 749,260 36.84×
      vecfp
      		 1,260 50,254 39.87×
      vecmath
      		 3,214 142,513 44.34×
      vecshuf
      		 679.73 24,439 35.95×
      vecwide
      		 28,526 1,085,622 38.06×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 7.4 269.59 36.43×
      bsearch
      		 235.81 10,405 44.12×
      bubblesort
      		 0.8 25.8 32.25×
      fibsearch
      		 260.29 9,408 36.14×
      heapsort
      		 8 347.59 43.45×
      hsearch
      		 6,839 268,729 39.29×
      insertionsort
      		 10.4 287.8 27.67×
      malloc
      		 2,106,770 76,276,219 36.21×
      mcontend
      		 90.87 10,220 112.47×
      mergesort
      		 24.8 1,139 45.92×
      qsort
      		 17.8 801.38 45.02×
      skiplist
      		 4,490 223,267 49.73×
      tree
      		 1.4 51.11 36.51×
      MemorySingleMultiScaling
      cache
      		 305,046 3,684,754 12.08×
      cachehammer
      		 189,032 5,930,538 31.37×
      cacheline
      		 54.17 3,312 61.15×
      l1cache
      		 899.24 10,590 11.78×
      memcpy
      		 364.7 10,919 29.94×
      memrate
      		 0.18 9.29 51.61×
      memthrash
      		 236.8 1,735 7.33×
      ptr-chase
      		 25,908,682 577,447,053 22.29×
      spinmem
      		 213.59 2,692 12.60×
      stream
      		 5.36 6,388 1191.87×
      vm
      		 84,064 301,238 3.58×

      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
      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-64 FAQs