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 0.592 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
2026-09-11T21:48:36.996681

Availability

REGION / IDSPOTONDEMAND
Columbus (US) / us-east5
1.1652 USD/h 3.8086 USD/h
Ashburn (US) / us-east4
2.1546 USD/h 3.8086 USD/h
Council Bluffs (US) / us-central1
2.1614 USD/h 3.8086 USD/h
The Dalles (US) / us-west1
2.1614 USD/h 3.8086 USD/h
Moncks Corner (US) / us-east1
2.1614 USD/h 3.8086 USD/h
Delhi (IN) / asia-south2
0.9626 USD/h 3.961 USD/h
Mumbai (IN) / asia-south1
1.1725 USD/h 3.961 USD/h
Eemshaven (NL) / europe-west4
0.8911 USD/h 3.9991 USD/h
Bangkok (TH) / asia-southeast3
0.934 USD/h 3.9991 USD/h
Stockholm (SE) / europe-north2
1.6604 USD/h 3.9991 USD/h
Queretaro (MX) / northamerica-south1
1.6787 USD/h 4.1514 USD/h
Tel Aviv (IL) / me-west1
1.4289 USD/h 4.1895 USD/h
St. Ghislain (BE) / europe-west1
0.6423 USD/h 4.1937 USD/h
Montréal (CA) / northamerica-northeast1
0.8346 USD/h 4.1937 USD/h
Johannesburg (ZA) / africa-south1
1.0061 USD/h 4.1937 USD/h
Toronto (CA) / northamerica-northeast2
1.4899 USD/h 4.1937 USD/h
Hamina (FI) / europe-north1
1.9284 USD/h 4.1937 USD/h
Las Vegas (US) / us-west4
2.1087 USD/h 4.2897 USD/h
London (GB) / europe-west2
1.6822 USD/h 4.3418 USD/h
Changhua County (TW) / asia-east1
1.6764 USD/h 4.41 USD/h
Milan (IT) / europe-west8
0.9649 USD/h 4.418 USD/h
Paris (FR) / europe-west9
1.4436 USD/h 4.418 USD/h
Dallas (US) / us-south1
0.8826 USD/h 4.4942 USD/h
Madrid (ES) / europe-southwest1
0.9718 USD/h 4.4942 USD/h
Frankfurt (DE) / europe-west3
2.4337 USD/h 4.4942 USD/h
Salt Lake City (US) / us-west3
0.8115 USD/h 4.5784 USD/h
Los Angeles (US) / us-west2
2.6132 USD/h 4.5784 USD/h
Warsaw (PL) / europe-central2
2.0367 USD/h 4.6085 USD/h
Doha (QA) / me-central1
2.0275 USD/h 4.6275 USD/h
Jurong West (SG) / asia-southeast1
2.5714 USD/h 4.6987 USD/h
Sydney (AU) / australia-southeast1
2.1957 USD/h 4.7608 USD/h
Osaka (JP) / asia-northeast2
1.7078 USD/h 4.8911 USD/h
Seoul (KR) / asia-northeast3
2.3331 USD/h 4.8911 USD/h
Tokyo (JP) / asia-northeast1
2.5412 USD/h 4.8911 USD/h
Melbourne (AU) / australia-southeast2
1.5933 USD/h 4.9512 USD/h
Zurich (CH) / europe-west6
2.3171 USD/h 4.9893 USD/h
Jakarta (ID) / asia-southeast2
1.4848 USD/h 5.1215 USD/h
Hong Kong / asia-east2
0.592 USD/h 5.3279 USD/h
Santiago (CL) / southamerica-west1
1.5213 USD/h 5.4464 USD/h
Osasco (BR) / southamerica-east1
0.9843 USD/h 6.0477 USD/h
Dammam (SA) / me-central2
1.116 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
97.19

System Resources and Accelerators

MEMORY
Memory Amount
512 GiB
Memory Amount Actual
512 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 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 1,917,397 ops/sec 4.91 50.00% 50.00% +122.00%
      Redis RPS (pipeline=16, SET) 48,891,942 ops/sec 11,681,410 ops/sec 4.19 20.00% 20.00% +33.20%
      PassMark Memory Mark (composite) 2,149 2,418 0.889 10.00% 10.00% -1.17%
      Memory bandwidth (read, 16 MB ~ L3) 355,678 MB/sec 108,140 MB/sec 3.29 10.00% 10.00% +12.60%
      PassMark single-thread CPU 2,442 Mops/s 2,365 Mops/s 1.03 10.00% 10.00% +0.30%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,807

      Geekbench Multi-Core

      Score: 17,904

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 62987
      Compression
      		 932628
      Encryption
      		 54355
      Extended Instructions
      		 67619
      Floating Point Maths
      		 173715
      Integer Maths
      		 242754
      Physics
      		 10872
      Prime Numbers
      		 520
      Single Threaded
      		 2442
      String Sorting
      		 123365

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2149
      Database Operations
      		 29376
      Memory Latency
      		 69
      Memory Read Cached
      		 21784
      Memory Read Uncached
      		 7975
      Memory Write
      		 7629

      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-highmem-64 FAQs