n2-highmem-96 by Google Cloud Platform

n2-highmem-96 is a 96 vCPUs 768 GB RAM server offered by Google Cloud Platform with 96 vCPUs, 768 GiB of memory and 0 GB of storage. The pricing starts at 0.623 USD per hour.
96 vCPU
768 GiB Memory
Spare SCore
89,967
(All-cores)
1,838
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
902096
Name
n2-highmem-96
Description
96 vCPUs 768 GB RAM
Family
n2
Hw Virt
Average Time To Start
145
Status
active
Observed At
2026-10-24T02:21:42.278050

Availability

REGION / IDSPOTONDEMAND
Council Bluffs (US) / us-central1
3.7724 USD/h 6.2887 USD/h
The Dalles (US) / us-west1
3.7724 USD/h 6.2887 USD/h
Moncks Corner (US) / us-east1
3.7724 USD/h 6.2887 USD/h
Columbus (US) / us-east5
3.7734 USD/h 6.2887 USD/h
Tel Aviv (IL) / me-west1
4.1489 USD/h 6.9175 USD/h
St. Ghislain (BE) / europe-west1
1.566 USD/h 6.9179 USD/h
Johannesburg (ZA) / africa-south1
1.9659 USD/h 6.9179 USD/h
Toronto (CA) / northamerica-northeast2
0.623 USD/h 6.9229 USD/h
Eemshaven (NL) / europe-west4
1.9236 USD/h 6.9229 USD/h
Montréal (CA) / northamerica-northeast1
3.1732 USD/h 6.9229 USD/h
Hamina (FI) / europe-north1
3.3619 USD/h 6.9233 USD/h
Las Vegas (US) / us-west4
3.9289 USD/h 7.082 USD/h
Ashburn (US) / us-east4
1.7666 USD/h 7.0822 USD/h
Changhua County (TW) / asia-east1
2.5227 USD/h 7.2816 USD/h
Milan (IT) / europe-west8
0.7165 USD/h 7.2949 USD/h
Paris (FR) / europe-west9
2.0415 USD/h 7.2949 USD/h
Dallas (US) / us-south1
1.3949 USD/h 7.4206 USD/h
Madrid (ES) / europe-southwest1
1.9142 USD/h 7.4206 USD/h
Delhi (IN) / asia-south2
0.6801 USD/h 7.5527 USD/h
Mumbai (IN) / asia-south1
2.6216 USD/h 7.5527 USD/h
Los Angeles (US) / us-west2
2.5492 USD/h 7.5535 USD/h
Salt Lake City (US) / us-west3
2.8915 USD/h 7.5535 USD/h
Melbourne (AU) / australia-southeast2
3.5234 USD/h 7.584 USD/h
Warsaw (PL) / europe-central2
2.4922 USD/h 7.6095 USD/h
Doha (QA) / me-central1
1.5064 USD/h 7.6407 USD/h
Jurong West (SG) / asia-southeast1
2.9556 USD/h 7.7575 USD/h
Tokyo (JP) / asia-northeast1
2.333 USD/h 8.0611 USD/h
Osaka (JP) / asia-northeast2
2.2493 USD/h 8.0758 USD/h
Seoul (KR) / asia-northeast3
2.3395 USD/h 8.0758 USD/h
London (GB) / europe-west2
1.6166 USD/h 8.1018 USD/h
Frankfurt (DE) / europe-west3
4.4628 USD/h 8.1018 USD/h
Berlin (DE) / europe-west10
1.1351 USD/h 8.1021 USD/h
Turin (IT) / europe-west12
1.5022 USD/h 8.1124 USD/h
Zurich (CH) / europe-west6
3.0058 USD/h 8.2384 USD/h
Jakarta (ID) / asia-southeast2
4.7829 USD/h 8.4556 USD/h
Hong Kong / asia-east2
2.4812 USD/h 8.7989 USD/h
Sydney (AU) / australia-southeast1
4.0846 USD/h 8.9226 USD/h
Santiago (CL) / southamerica-west1
2.3038 USD/h 8.9928 USD/h
Osasco (BR) / southamerica-east1
2.4219 USD/h 9.9821 USD/h
Dammam (SA) / me-central2
1.6669 USD/h 10.0619 USD/h

Processor

vCPUs
96
CPU Allocation
Dedicated
CPU Cores
48
CPU Speed
2.6 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
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
1 MiB
CPU L2 Cache Total
60 MiB
CPU L3 Cache
54 MiB
CPU L3 Cache Total
108 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, 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, arat, avx512vbmi, umip, avx512_vbmi2, gfni, vaes, vpclmulqdq, avx512_vnni, avx512_bitalg, avx512_vpopcntdq, rdpid, fsrm, md_clear, arch_capabilities
Ecpus
48.9
Scalability
50.94

System Resources and Accelerators

MEMORY
Memory Amount
768 GiB
Memory Amount Actual
768 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 virtual server featuring ninety-six dedicated vCPUs and high memory bandwidth for demanding database and caching workloads.

      Memory OptimizedGeneral Purpose

      Google Cloud Platform n2-highmem-96 is a memory-optimized instance featuring 96 vCPUs and 768 GB of RAM, powered by a 2.6 GHz Intel Xeon processor. Operating on the x86_64 architecture with dedicated CPU allocation, this instance provides 8 GB of memory per vCPU but does not include local storage or GPUs. Benchmark data highlights strong multi-core CPU performance, high memory bandwidth, and excellent database operation throughput, though single-core performance remains average. This resource profile makes the instance highly suitable for memory-intensive workloads, including large databases, in-memory caches, and high-throughput web serving.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      4Score
      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) 12,275,521 ops/sec 1,919,289 ops/sec 6.3 50.00% 50.00% +150.00%
      Redis RPS (pipeline=16, SET) 60,530,349 ops/sec 11,728,058 ops/sec 5.1 20.00% 20.00% +39.00%
      PassMark Memory Mark (composite) 2,774 2,416 1.2 10.00% 10.00% +1.80%
      Memory bandwidth (read, 16 MB ~ L3) 346,493 MB/sec 108,466 MB/sec 3.2 10.00% 10.00% +12.00%
      PassMark single-thread CPU 2,346 Mops/s 2,365 Mops/s 0.96 10.00% 10.00% -0.41%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,571

      Geekbench Multi-Core

      Score: 17,004

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 74,382
      Compression
      		 1,424,439
      Encryption
      		 83,867
      Extended Instructions
      		 80,568
      Floating Point Maths
      		 200,569
      Integer Maths
      		 391,928
      Physics
      		 8,088
      Prime Numbers
      		 474
      Single Threaded
      		 2,346
      String Sorting
      		 193,235

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2,774
      Database Operations
      		 30,990
      Memory Latency
      		 55
      Memory Read Cached
      		 23,701
      Memory Read Uncached
      		 12,014
      Memory Write
      		 11,074

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 211.23 256.36 1.21×
      bitops
      		 127,076 6,194,541 48.75×
      branch
      		 133,624 10,162,241 76.05×
      funccall
      		 617.92 30,345 49.11×
      funcret
      		 11,337 753,608 66.47×
      hash
      		 147,963 10,201,939 68.95×
      intmath
      		 59,610 3,511,311 58.90×
      nop
      		 183,791 7,828,705 42.60×
      prime
      		 382,401 20,144,603 52.68×
      rotate
      		 95,177 4,860,163 51.06×
      str
      		 846,532 44,173,922 52.18×
      wcs
      		 592,253 24,790,792 41.86×
      CryptographySingleMultiScaling
      crypt
      		 2,766 122,906 44.44×
      CompressionSingleMultiScaling
      jpeg
      		 688.67 42,389 61.55×
      zlib
      		 39.08 4,108 105.13×
      HypervisorSingleMultiScaling
      clock
      		 34,069 252,239 7.40×
      clone
      		 452.55 8,872 19.61×
      context
      		 4,582 333,492 72.78×
      cpu-sched
      		 59.4 5,975 100.59×
      eventfd
      		 59,501 2,928,545 49.22×
      fault
      		 16,541 238,172 14.40×
      fork
      		 5,236 62,891 12.01×
      getrandom
      		 48,349 2,637,449 54.55×
      hrtimers
      		 177,375 11,880,941 66.98×
      mprotect
      		 791,126 16,822,248 21.26×
      mtx
      		 12,578,311 2,719,972,776 216.24×
      munmap
      		 3,681 70,556 19.17×
      null
      		 723,126 43,411,125 60.03×
      pipe
      		 880,435 55,819,191 63.40×
      priv-instr
      		 747,317 14,531,618 19.45×
      resched
      		 10,342,169 9,279,431 0.90×
      switch
      		 83,804 21,742,986 259.45×
      timermix
      		 205,284 15,776,219 76.85×
      tlb-shootdown
      		 7,625 121,427 15.93×
      tsc
      		 747,875 52,739,284 70.52×
      usersyscall
      		 625,503 13,613,406 21.76×
      vdso
      		 106,858,906 5,914,020,415 55.34×
      vfork
      		 32,979 141,280 4.28×
      x86syscall
      		 8,325,558 552,236,935 66.33×
      yield
      		 85,272,257 94,221,941 1.10×
      zero
      		 4,366,829 237,940,839 54.49×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 14,418 888,933 61.65×
      expmath
      		 2,807 196,881 70.15×
      fma
      		 622,388 51,809,302 83.24×
      fp
      		 166.31 9,617 57.82×
      fractal
      		 4.8 342.34 71.32×
      hyperbolic
      		 2,989 211,823 70.87×
      logmath
      		 4,722 325,247 68.88×
      matrix
      		 3,413 245,760 72.01×
      matrix-3d
      		 785.05 12,693 16.17×
      monte-carlo
      		 247.45 15,963 64.51×
      mpfr
      		 1,374 70,462 51.27×
      powmath
      		 1,642 116,698 71.06×
      trig
      		 1,922 116,538 60.62×
      veccmp
      		 19,981 916,359 45.86×
      vecfp
      		 1,486 87,179 58.65×
      vecmath
      		 3,147 217,978 69.27×
      vecshuf
      		 648.24 33,639 51.89×
      vecwide
      		 31,060 1,646,773 53.02×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 7.8 383.79 49.20×
      bsearch
      		 241.17 15,386 63.80×
      bubblesort
      		 1 38.4 38.40×
      fibsearch
      		 280.75 16,692 59.46×
      heapsort
      		 9.2 518.19 56.33×
      hsearch
      		 7,116 379,949 53.39×
      insertionsort
      		 10.2 288 28.24×
      malloc
      		 2,646,150 66,456,993 25.11×
      mcontend
      		 67.33 17,102 254.01×
      mergesort
      		 26.2 1,712 65.34×
      qsort
      		 20.2 1,007 49.87×
      skiplist
      		 5,281 369,535 69.98×
      tree
      		 1.6 57.56 35.98×
      MemorySingleMultiScaling
      cache
      		 344,533 2,325,716 6.75×
      cachehammer
      		 365,622 14,022,047 38.35×
      cacheline
      		 55.76 3,323 59.60×
      l1cache
      		 877.07 16,900 19.27×
      memcpy
      		 396.08 18,718 47.26×
      memrate
      		 1.78 33.55 18.85×
      memthrash
      		 304.24 1,456 4.79×
      ptr-chase
      		 33,599,829 889,876,416 26.48×
      spinmem
      		 225.19 4,399 19.53×
      stream
      		 18.48 30,243 1636.55×
      vm
      		 112,273 564,786 5.03×

      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
      n2-highcpu-2 22 GiB0
      n2-standard-2 28 GiB0
      n2-highmem-2 216 GiB0
      n2-highcpu-4 44 GiB0
      n2-standard-4 416 GiB0
      n2-highmem-4 432 GiB0
      n2-highcpu-8 88 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      n2-highmem-96 FAQs