n4-highcpu-64 by Google Cloud Platform

n4-highcpu-64 is a 64 vCPUs, 128 GB RAM server offered by Google Cloud Platform with 64 vCPUs, 128 GiB of memory and 0 GB of storage. The pricing starts at 0.3619 USD per hour.
64 vCPU
128 GiB Memory
Spare SCore
58,262
(All-cores)
1,786
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
1750023
Name
n4-highcpu-64
Description
64 vCPUs, 128 GB RAM
Family
n4
Hw Virt
Average Time To Start
20
Status
active
Observed At
2026-09-17T10:07:32.467558

Availability

REGION / IDSPOTONDEMAND
Columbus (US) / us-east5
0.7873 USD/h 2.4493 USD/h
Ashburn (US) / us-east4
1.455 USD/h 2.4493 USD/h
Council Bluffs (US) / us-central1
1.4591 USD/h 2.4493 USD/h
The Dalles (US) / us-west1
1.4591 USD/h 2.4493 USD/h
Moncks Corner (US) / us-east1
1.4591 USD/h 2.4493 USD/h
Delhi (IN) / asia-south2
0.6496 USD/h 2.5473 USD/h
Mumbai (IN) / asia-south1
0.7163 USD/h 2.5473 USD/h
Eemshaven (NL) / europe-west4
0.6015 USD/h 2.5717 USD/h
Stockholm (SE) / europe-north2
1.0145 USD/h 2.5717 USD/h
Bangkok (TH) / asia-southeast3
0.5709 USD/h 2.5718 USD/h
Queretaro (MX) / northamerica-south1
1.0255 USD/h 2.6697 USD/h
Tel Aviv (IL) / me-west1
0.8731 USD/h 2.6942 USD/h
St. Ghislain (BE) / europe-west1
0.4131 USD/h 2.6969 USD/h
Montréal (CA) / northamerica-northeast1
0.5637 USD/h 2.6969 USD/h
Johannesburg (ZA) / africa-south1
0.647 USD/h 2.6969 USD/h
Toronto (CA) / northamerica-northeast2
1.054 USD/h 2.6969 USD/h
Hamina (FI) / europe-north1
1.2396 USD/h 2.6969 USD/h
Las Vegas (US) / us-west4
1.2881 USD/h 2.7586 USD/h
London (GB) / europe-west2
1.0278 USD/h 2.7922 USD/h
Changhua County (TW) / asia-east1
1.0781 USD/h 2.836 USD/h
Milan (IT) / europe-west8
0.5891 USD/h 2.8412 USD/h
Paris (FR) / europe-west9
0.9746 USD/h 2.8412 USD/h
Madrid (ES) / europe-southwest1
0.5937 USD/h 2.8902 USD/h
Dallas (US) / us-south1
0.596 USD/h 2.8902 USD/h
Frankfurt (DE) / europe-west3
1.7213 USD/h 2.8902 USD/h
Salt Lake City (US) / us-west3
0.5736 USD/h 2.9443 USD/h
Los Angeles (US) / us-west2
1.6805 USD/h 2.9443 USD/h
Warsaw (PL) / europe-central2
1.2445 USD/h 2.9636 USD/h
Doha (QA) / me-central1
1.3037 USD/h 2.9759 USD/h
Jurong West (SG) / asia-southeast1
1.6532 USD/h 3.0217 USD/h
Sydney (AU) / australia-southeast1
1.412 USD/h 3.0616 USD/h
Osaka (JP) / asia-northeast2
1.1529 USD/h 3.1454 USD/h
Seoul (KR) / asia-northeast3
1.5758 USD/h 3.1454 USD/h
Tokyo (JP) / asia-northeast1
1.7158 USD/h 3.1454 USD/h
Melbourne (AU) / australia-southeast2
0.9732 USD/h 3.1841 USD/h
Zurich (CH) / europe-west6
1.5649 USD/h 3.2086 USD/h
Jakarta (ID) / asia-southeast2
0.9549 USD/h 3.2935 USD/h
Hong Kong / asia-east2
0.3619 USD/h 3.4263 USD/h
Santiago (CL) / southamerica-west1
0.9292 USD/h 3.5025 USD/h
Osasco (BR) / southamerica-east1
0.6015 USD/h 3.8892 USD/h
Dammam (SA) / me-central2
0.7543 USD/h 3.9188 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
32.6
Scalability
101.88

System Resources and Accelerators

MEMORY
Memory Amount
128 GiB
Memory Amount Actual
128 GiB
GPU
GPU Count
0
GPU Memory Min
0 MiB
GPU Memory Total
0 MiB
GPUs
    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 server featuring sixty-four dedicated cores and advanced matrix extensions for accelerated processing and database workloads.

      Compute OptimizedGeneral Purpose

      Google Cloud Platform n4-highcpu-64 is a compute-optimized x86_64 server featuring 64 dedicated vCPUs across 32 physical Intel cores and 128 GB of RAM. Lacking local storage and GPU accelerators, this instance relies on its high-density CPU configuration and a 260 MB L3 cache. It supports advanced instruction sets like AVX-512 and Intel AMX. Benchmark results place the server in the top tier for database operations and image processing, with strong performance in software compilation, ray tracing, and multi-core processing. It also exhibits strong throughput for Redis SET operations and static web serving. The 2.0 GB of RAM per core makes it highly efficient for compute-bound tasks, though it is less suited for memory-heavy applications. This server is recommended for high-throughput web serving, software compilation, cryptography, and CPU-based machine learning inference.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      3.29Score
      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) 9,557,191 ops/sec 1,919,696 ops/sec 4.98 50.00% 50.00% +123.00%
      Redis RPS (pipeline=16, SET) 49,540,796 ops/sec 11,736,081 ops/sec 4.22 20.00% 20.00% +33.40%
      PassMark Memory Mark (composite) 2,616 2,418 1.08 10.00% 10.00% +0.77%
      Memory bandwidth (read, 16 MB ~ L3) 241,127 MB/sec 108,260 MB/sec 2.23 10.00% 10.00% +8.35%
      PassMark single-thread CPU 2,711 Mops/s 2,365 Mops/s 1.15 10.00% 10.00% +1.41%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,881

      Geekbench Multi-Core

      Score: 18,694

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 69148
      Compression
      		 1008183
      Encryption
      		 60374
      Extended Instructions
      		 75345
      Floating Point Maths
      		 191088
      Integer Maths
      		 259251
      Physics
      		 11651
      Prime Numbers
      		 561
      Single Threaded
      		 2711
      String Sorting
      		 135188

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2616
      Database Operations
      		 33232
      Memory Latency
      		 58
      Memory Read Cached
      		 23822
      Memory Read Uncached
      		 10958
      Memory Write
      		 10188

      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

      INSTANCEvCPUsMEMORYGPUs
      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

      INSTANCEVENDORvCPUsMEMORYGPUs

      n4-highcpu-64 FAQs