n2-highmem-48 by Google Cloud Platform

n2-highmem-48 is a 48 vCPUs 384 GB RAM server offered by Google Cloud Platform with 48 vCPUs, 384 GiB of memory and 0 GB of storage. The pricing starts at 0.3115 USD per hour.
48 vCPU
384 GiB Memory
Spare SCore
45,193
(All-cores)
1,842
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
902048
Name
n2-highmem-48
Description
48 vCPUs 384 GB RAM
Family
n2
Hw Virt
Average Time To Start
20
Status
active
Observed At
2026-10-31T15:45:34.030627

Availability

REGION / IDSPOTONDEMAND
Council Bluffs (US) / us-central1
1.8862 USD/h 3.1443 USD/h
The Dalles (US) / us-west1
1.8862 USD/h 3.1443 USD/h
Moncks Corner (US) / us-east1
1.8862 USD/h 3.1443 USD/h
Columbus (US) / us-east5
1.8867 USD/h 3.1443 USD/h
Tel Aviv (IL) / me-west1
2.0745 USD/h 3.4588 USD/h
St. Ghislain (BE) / europe-west1
0.7439 USD/h 3.4589 USD/h
Johannesburg (ZA) / africa-south1
1.0815 USD/h 3.4589 USD/h
Toronto (CA) / northamerica-northeast2
0.3115 USD/h 3.4615 USD/h
Eemshaven (NL) / europe-west4
1.0583 USD/h 3.4615 USD/h
Montréal (CA) / northamerica-northeast1
1.7456 USD/h 3.4615 USD/h
Hamina (FI) / europe-north1
1.7647 USD/h 3.4617 USD/h
Las Vegas (US) / us-west4
2.0627 USD/h 3.541 USD/h
Ashburn (US) / us-east4
0.9717 USD/h 3.5411 USD/h
Changhua County (TW) / asia-east1
1.3876 USD/h 3.6408 USD/h
Milan (IT) / europe-west8
0.394 USD/h 3.6474 USD/h
Paris (FR) / europe-west9
0.9698 USD/h 3.6474 USD/h
Dallas (US) / us-south1
0.6626 USD/h 3.7103 USD/h
Madrid (ES) / europe-southwest1
1.0047 USD/h 3.7103 USD/h
Delhi (IN) / asia-south2
0.34 USD/h 3.7764 USD/h
Mumbai (IN) / asia-south1
1.2453 USD/h 3.7764 USD/h
Los Angeles (US) / us-west2
1.3383 USD/h 3.7767 USD/h
Salt Lake City (US) / us-west3
1.518 USD/h 3.7767 USD/h
Melbourne (AU) / australia-southeast2
1.6733 USD/h 3.792 USD/h
Warsaw (PL) / europe-central2
1.3086 USD/h 3.8048 USD/h
Doha (QA) / me-central1
0.8285 USD/h 3.8204 USD/h
Jurong West (SG) / asia-southeast1
1.5517 USD/h 3.8787 USD/h
Tokyo (JP) / asia-northeast1
1.2248 USD/h 4.0306 USD/h
Seoul (KR) / asia-northeast3
1.1111 USD/h 4.0379 USD/h
Osaka (JP) / asia-northeast2
1.1812 USD/h 4.0379 USD/h
London (GB) / europe-west2
0.8487 USD/h 4.0509 USD/h
Frankfurt (DE) / europe-west3
2.3428 USD/h 4.0509 USD/h
Berlin (DE) / europe-west10
0.5961 USD/h 4.051 USD/h
Turin (IT) / europe-west12
0.7889 USD/h 4.0562 USD/h
Zurich (CH) / europe-west6
1.5781 USD/h 4.1192 USD/h
Jakarta (ID) / asia-southeast2
2.272 USD/h 4.2278 USD/h
Hong Kong / asia-east2
1.1786 USD/h 4.3994 USD/h
Sydney (AU) / australia-southeast1
2.1447 USD/h 4.4613 USD/h
Santiago (CL) / southamerica-west1
1.2097 USD/h 4.4964 USD/h
Osasco (BR) / southamerica-east1
1.1502 USD/h 4.991 USD/h
Dammam (SA) / me-central2
0.7918 USD/h 5.0309 USD/h

Processor

vCPUs
48
CPU Allocation
Dedicated
CPU Cores
24
CPU Speed
2.8 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU L1D Cache
32 KiB
CPU L1D Cache Total
768 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
768 KiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
24 MiB
CPU L3 Cache
33 MiB
CPU L3 Cache Total
66 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, clflushopt, clwb, avx512cd, avx512bw, avx512vl, xsaveopt, xsavec, xgetbv1, xsaves, arat, avx512_vnni, md_clear, arch_capabilities
Ecpus
24.5
Scalability
51.04

System Resources and Accelerators

MEMORY
Memory Amount
384 GiB
Memory Amount Actual
384 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 dedicated Intel Xeon processors and high memory bandwidth for demanding database and enterprise workloads.

      Memory OptimizedGeneral Purpose

      Google Cloud Platform n2-highmem-48 is an x86_64 virtual machine instance configured with 48 dedicated vCPUs and 384.0 GB of RAM, providing a high memory-to-core ratio of 8.0 GB per vCPU. Powered by an Intel Xeon processor running at 2.8 GHz, it features 24 physical cores, a 33 MB L3 cache, and supports AVX-512 instructions. This instance does not include local storage or GPUs. Benchmark data highlights strong performance in uncached large-block memory bandwidth, with reads at 212.65 GB/sec and writes at 98.19 GB/sec, alongside a high static web serving throughput of 47.78 GB/sec. Other compute and database benchmarks fall within the average range. The n2-highmem-48 is qualitatively cost-efficient for memory-intensive workloads, making it highly suitable for large databases, in-memory caching, software compilation, and high-throughput web serving.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      2.4Score
      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) 6,277,585 ops/sec 1,918,343 ops/sec 3.3 50.00% 50.00% +82.00%
      Redis RPS (pipeline=16, SET) 32,087,175 ops/sec 11,704,734 ops/sec 2.7 20.00% 20.00% +22.00%
      PassMark Memory Mark (composite) 2,721 2,416 1.1 10.00% 10.00% +0.96%
      Memory bandwidth (read, 16 MB ~ L3) 229,005 MB/sec 108,466 MB/sec 2.1 10.00% 10.00% +7.70%
      PassMark single-thread CPU 2,015 Mops/s 2,365 Mops/s 0.83 10.00% 10.00% -1.80%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,203

      Geekbench Multi-Core

      Score: 11,383

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 38,235
      Compression
      		 659,052
      Encryption
      		 20,384
      Extended Instructions
      		 39,422
      Floating Point Maths
      		 80,006
      Integer Maths
      		 148,916
      Physics
      		 4,056
      Prime Numbers
      		 208
      Single Threaded
      		 2,015
      String Sorting
      		 76,617

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2,721
      Database Operations
      		 16,978
      Memory Latency
      		 50
      Memory Read Cached
      		 24,209
      Memory Read Uncached
      		 10,388
      Memory Write
      		 10,040

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 252.88 156.7 0.62×
      bitops
      		 107,524 2,968,853 27.61×
      branch
      		 153,744 5,601,007 36.43×
      funccall
      		 543.23 13,459 24.78×
      funcret
      		 11,343 385,452 33.98×
      hash
      		 126,043 4,328,844 34.34×
      intmath
      		 22,376 799,033 35.71×
      nop
      		 191,411 3,965,795 20.72×
      prime
      		 314,901 8,406,372 26.70×
      rotate
      		 96,636 3,176,678 32.87×
      str
      		 737,927 19,336,662 26.20×
      wcs
      		 481,360 11,983,703 24.90×
      CryptographySingleMultiScaling
      crypt
      		 2,443 56,973 23.33×
      CompressionSingleMultiScaling
      jpeg
      		 581.57 16,625 28.59×
      zlib
      		 46.91 1,881 40.09×
      HypervisorSingleMultiScaling
      clock
      		 27,551 195,232 7.09×
      clone
      		 300.78 4,823 16.04×
      context
      		 2,567 71,389 27.81×
      cpu-sched
      		 73.51 3,021 41.10×
      eventfd
      		 46,024 1,251,992 27.20×
      fault
      		 11,097 143,388 12.92×
      fork
      		 3,672 58,177 15.84×
      getrandom
      		 44,755 1,307,347 29.21×
      hrtimers
      		 233,299 4,721,215 20.24×
      mprotect
      		 605,712 7,331,907 12.10×
      mtx
      		 10,295,039 1,141,810,760 110.91×
      munmap
      		 2,482 49,769 20.05×
      null
      		 289,629 7,118,927 24.58×
      pipe
      		 851,602 12,189,994 14.31×
      priv-instr
      		 558,263 10,274,312 18.40×
      resched
      		 4,066,277 2,491,335 0.61×
      switch
      		 84,969 7,566,328 89.05×
      timermix
      		 186,679 6,264,471 33.56×
      tlb-shootdown
      		 6,988 65,308 9.35×
      tsc
      		 997,488 32,932,263 33.02×
      usersyscall
      		 383,157 7,869,421 20.54×
      vdso
      		 82,820,291 2,785,056,684 33.63×
      vfork
      		 23,581 139,766 5.93×
      x86syscall
      		 3,363,231 80,787,052 24.02×
      yield
      		 27,254,089 29,543,939 1.08×
      zero
      		 1,996,487 51,191,211 25.64×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 16,174 440,985 27.27×
      expmath
      		 2,685 98,268 36.60×
      fma
      		 547,688 21,367,115 39.01×
      fp
      		 117.41 3,690 31.42×
      fractal
      		 5 173.12 34.62×
      hyperbolic
      		 2,804 104,609 37.31×
      logmath
      		 4,531 160,034 35.32×
      matrix
      		 2,997 114,969 38.36×
      matrix-3d
      		 629.85 6,496 10.31×
      monte-carlo
      		 139.64 3,619 25.92×
      mpfr
      		 1,211 31,184 25.76×
      powmath
      		 1,576 57,844 36.71×
      trig
      		 1,694 52,979 31.28×
      veccmp
      		 15,598 381,206 24.44×
      vecfp
      		 1,298 38,457 29.63×
      vecmath
      		 2,192 81,735 37.29×
      vecshuf
      		 564.02 14,475 25.66×
      vecwide
      		 23,780 613,019 25.78×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 7.2 199.79 27.75×
      bsearch
      		 242.17 6,549 27.04×
      bubblesort
      		 0.8 19.2 24.00×
      fibsearch
      		 244.61 6,733 27.53×
      heapsort
      		 8.8 249.59 28.36×
      hsearch
      		 4,920 147,768 30.04×
      insertionsort
      		 8.2 192 23.41×
      malloc
      		 2,014,448 39,266,151 19.49×
      mcontend
      		 66.9 9,642 144.13×
      mergesort
      		 23.2 734.97 31.68×
      qsort
      		 14.8 403.99 27.30×
      skiplist
      		 4,880 162,098 33.22×
      tree
      		 0.8 23.99 29.99×
      MemorySingleMultiScaling
      cache
      		 232,715 873,954 3.76×
      cachehammer
      		 368,607 10,584,384 28.71×
      cacheline
      		 15.37 1,430 93.03×
      l1cache
      		 226.91 5,798 25.55×
      memcpy
      		 347.86 8,960 25.76×
      memrate
      		 1.37 17.38 12.69×
      memthrash
      		 199.89 1,105 5.53×
      ptr-chase
      		 21,110,076 465,812,169 22.07×
      spinmem
      		 222.39 2,039 9.17×
      stream
      		 15.49 13,195 851.85×
      vm
      		 57,655 301,038 5.22×

      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-48 FAQs