n4d-highcpu-96 by Google Cloud Platform

n4d-highcpu-96 is a 96 vCPUs, 192 GB RAM server offered by Google Cloud Platform with 96 vCPUs, 192 GiB of memory and 0 GB of storage. The pricing starts at 0.6657 USD per hour.
96 vCPU
192 GiB Memory
Spare SCore
165,189
(All-cores)
3,441
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
1751208
Name
n4d-highcpu-96
Description
96 vCPUs, 192 GB RAM
Family
n4d
Hw Virt
Average Time To Start
16
Status
active
Observed At
2026-10-21T07:22:00.720040

Availability

REGION / IDSPOTONDEMAND
Mumbai (IN) / asia-south1
1.3158 USD/h 2.6077 USD/h
Moncks Corner (US) / us-east1
1.0095 USD/h 3.4301 USD/h
The Dalles (US) / us-west1
1.0568 USD/h 3.4301 USD/h
Columbus (US) / us-east5
1.8263 USD/h 3.4301 USD/h
Ashburn (US) / us-east4
1.9181 USD/h 3.4301 USD/h
Council Bluffs (US) / us-central1
2.0565 USD/h 3.4301 USD/h
Delhi (IN) / asia-south2
1.1652 USD/h 3.5668 USD/h
Eemshaven (NL) / europe-west4
2.1612 USD/h 3.6025 USD/h
Tel Aviv (IL) / me-west1
0.6657 USD/h 3.7729 USD/h
St. Ghislain (BE) / europe-west1
1.1332 USD/h 3.776 USD/h
Hamina (FI) / europe-north1
1.5629 USD/h 3.776 USD/h
Las Vegas (US) / us-west4
1.0429 USD/h 3.8637 USD/h
London (GB) / europe-west2
2.3447 USD/h 3.9096 USD/h
Frankfurt (DE) / europe-west3
2.1531 USD/h 4.0483 USD/h
Salt Lake City (US) / us-west3
2.4724 USD/h 4.1235 USD/h
Jurong West (SG) / asia-southeast1
2.3681 USD/h 4.231 USD/h
Dammam (SA) / me-central2
1.459 USD/h 5.4889 USD/h

Processor

vCPUs
96
CPU Allocation
Dedicated
CPU Cores
48
CPU Architecture
x86_64
CPU Manufacturer
AMD
CPU Family
EPYC
CPU Model
9B45
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
48 MiB
CPU L3 Cache
32 MiB
CPU L3 Cache Total
192 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, ht, syscall, nx, mmxext, fxsr_opt, pdpe1gb, rdtscp, lm, constant_tsc, rep_good, nopl, xtopology, nonstop_tsc, cpuid, extd_apicid, tsc_known_freq, pni, pclmulqdq, ssse3, fma, cx16, pcid, sse4_1, sse4_2, x2apic, movbe, popcnt, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, cmp_legacy, cr8_legacy, abm, sse4a, misalignsse, 3dnowprefetch, osvw, topoext, ssbd, ibrs, ibpb, stibp, ibrs_enhanced, vmmcall, fsgsbase, tsc_adjust, bmi1, avx2, smep, bmi2, invpcid, avx512f, avx512dq, rdseed, adx, smap, avx512ifma, clflushopt, clwb, avx512cd, sha_ni, avx512bw, avx512vl, xsaveopt, xsavec, xgetbv1, xsaves, avx_vnni, avx512_bf16, clzero, xsaveerptr, wbnoinvd, arat, avx512vbmi, umip, pku, ospke, avx512_vbmi2, gfni, vaes, vpclmulqdq, avx512_vnni, avx512_bitalg, avx512_vpopcntdq, rdpid, movdiri, movdir64b, avx512_vp2intersect, flush_l1d
Ecpus
48
Scalability
50

System Resources and Accelerators

MEMORY
Memory Amount
192 GiB
Memory Amount Actual
192 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 high-density, compute-optimized virtual machine delivering top-tier multi-core performance and advanced vector processing for demanding CPU-bound workloads.

      Compute Optimized

      Google Cloud Platform n4d-highcpu-96 is a compute-optimized instance featuring 96 vCPUs and 192 GB of RAM, powered by a dedicated AMD EPYC 9B45 processor. Built on the x86_64 architecture, it provides 48 physical cores with multithreading and a 2.0 GB per vCPU memory ratio. The instance does not include local storage or GPU accelerators. In benchmark testing, the n4d-highcpu-96 delivers top-tier performance in both single-core and multi-core CPU workloads, including software compilation, cryptography, and database operations. It supports advanced vector instructions like AVX-512, enabling high-throughput processing. This instance is highly suited for compute-intensive workloads such as CI/CD pipelines, static web serving, high-performance computing, and small-to-medium scale language model inference.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      6.3Score
      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) 21,415,415 ops/sec 1,918,343 ops/sec 11 50.00% 50.00% +230.00%
      Redis RPS (pipeline=16, SET) 116,970,004 ops/sec 11,704,734 ops/sec 10 20.00% 20.00% +58.00%
      PassMark Memory Mark (composite) 2,969 2,416 1.2 10.00% 10.00% +1.80%
      Memory bandwidth (read, 16 MB ~ L3) 384,104 MB/sec 108,420 MB/sec 3.5 10.00% 10.00% +13.00%
      PassMark single-thread CPU 3,469 Mops/s 2,365 Mops/s 1.5 10.00% 10.00% +4.10%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 2,577

      Geekbench Multi-Core

      Score: 27,814

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 115,690
      Compression
      		 2,142,489
      Encryption
      		 116,854
      Extended Instructions
      		 167,014
      Floating Point Maths
      		 356,030
      Integer Maths
      		 583,483
      Physics
      		 18,550
      Prime Numbers
      		 844
      Single Threaded
      		 3,469
      String Sorting
      		 261,600

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2,969
      Database Operations
      		 40,067
      Memory Latency
      		 75
      Memory Read Cached
      		 31,261
      Memory Read Uncached
      		 29,403
      Memory Write
      		 23,161

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 516.65 248.94 0.48×
      bitops
      		 210,717 11,606,910 55.08×
      branch
      		 168,139 13,020,010 77.44×
      funccall
      		 829.18 51,387 61.97×
      funcret
      		 24,618 1,720,218 69.88×
      hash
      		 199,539 14,132,240 70.82×
      intmath
      		 73,685 4,045,512 54.90×
      nop
      		 395,009 22,558,780 57.11×
      prime
      		 571,851 34,820,962 60.89×
      rotate
      		 130,298 6,357,733 48.79×
      str
      		 1,429,882 80,867,128 56.56×
      wcs
      		 983,807 50,569,371 51.40×
      CryptographySingleMultiScaling
      crypt
      		 4,977 256,462 51.53×
      CompressionSingleMultiScaling
      jpeg
      		 1,161 69,406 59.77×
      zlib
      		 69.81 5,669 81.21×
      HypervisorSingleMultiScaling
      clock
      		 43,380 324,529 7.48×
      clone
      		 347.7 11,489 33.04×
      context
      		 8,274 647,866 78.30×
      cpu-sched
      		 63.75 6,156 96.56×
      eventfd
      		 68,298 5,791,374 84.80×
      fault
      		 39,595 210,061 5.31×
      fork
      		 6,069 108,224 17.83×
      getrandom
      		 89,899 4,663,066 51.87×
      hrtimers
      		 218,185 1,224,029 5.61×
      mprotect
      		 723,404 25,505,980 35.26×
      mtx
      		 51,292,181 5,244,225,414 102.24×
      munmap
      		 4,892 117,244 23.97×
      null
      		 1,361,690 104,323,962 76.61×
      pipe
      		 2,584,208 64,806,303 25.08×
      priv-instr
      		 1,328,894 32,327,737 24.33×
      resched
      		 14,130,197 14,612,814 1.03×
      switch
      		 129,073 17,145,434 132.84×
      timermix
      		 506,337 5,261,123 10.39×
      tlb-shootdown
      		 21,333 287,064 13.46×
      tsc
      		 811,728 76,618,110 94.39×
      usersyscall
      		 1,040,508 30,885,634 29.68×
      vdso
      		 99,168,653 7,685,415,551 77.50×
      vfork
      		 39,586 191,485 4.84×
      x86syscall
      		 17,705,393 1,452,000,224 82.01×
      yield
      		 134,843,859 148,997,118 1.10×
      zero
      		 7,234,267 442,595,664 61.18×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 16,069 898,012 55.89×
      expmath
      		 3,676 230,560 62.72×
      fma
      		 1,424,970 97,703,662 68.57×
      fp
      		 201.06 14,327 71.26×
      fractal
      		 8.2 541.98 66.10×
      hyperbolic
      		 5,000 361,895 72.38×
      logmath
      		 5,227 382,369 73.16×
      matrix
      		 8,528 329,441 38.63×
      matrix-3d
      		 1,392 13,698 9.84×
      monte-carlo
      		 420.98 31,903 75.78×
      mpfr
      		 2,225 140,009 62.92×
      powmath
      		 1,685 126,046 74.80×
      trig
      		 2,231 159,202 71.37×
      veccmp
      		 27,685 1,705,562 61.61×
      vecfp
      		 2,278 161,674 70.98×
      vecmath
      		 4,344 320,280 73.73×
      vecshuf
      		 916.55 53,336 58.19×
      vecwide
      		 37,042 2,247,433 60.67×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 11.6 648.18 55.88×
      bsearch
      		 320.93 22,464 70.00×
      bubblesort
      		 1.2 59.6 49.67×
      fibsearch
      		 388.86 23,091 59.38×
      heapsort
      		 13.2 843.13 63.87×
      hsearch
      		 12,251 665,614 54.33×
      insertionsort
      		 14.6 492.6 33.74×
      malloc
      		 4,811,916 158,939,247 33.03×
      mcontend
      		 122.51 16,310 133.13×
      mergesort
      		 36.2 2,428 67.07×
      qsort
      		 23.8 1,525 64.09×
      skiplist
      		 7,686 577,850 75.19×
      tree
      		 2.4 90.39 37.66×
      MemorySingleMultiScaling
      cache
      		 1,047,232 1,938,887 1.85×
      cachehammer
      		 284,530 16,945,605 59.56×
      cacheline
      		 58.98 4,650 78.84×
      l1cache
      		 1,259 36,673 29.13×
      memcpy
      		 743.69 34,430 46.30×
      memrate
      		 0.96 22.2 23.13×
      memthrash
      		 311.46 2,737 8.79×
      ptr-chase
      		 73,306,247 813,017,436 11.09×
      spinmem
      		 356.99 7,449 20.86×
      stream
      		 147.22 148,692 1010.00×
      vm
      		 235,588 304,722 1.29×

      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
      n4d-highcpu-2 24 GiB0
      n4d-standard-2 28 GiB0
      n4d-highmem-2 216 GiB0
      n4d-highcpu-4 48 GiB0
      n4d-standard-4 416 GiB0
      n4d-highmem-4 432 GiB0
      n4d-highcpu-8 816 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      n4d-highcpu-96 FAQs