n4-highmem-8 by Google Cloud Platform

n4-highmem-8 is a 8 vCPUs, 64 GB RAM server offered by Google Cloud Platform with 8 vCPUs, 64 GiB of memory and 0 GB of storage. The pricing starts at 0.0779 USD per hour.
8 vCPU
64 GiB Memory
Spare SCore
6,753
(All-cores)
1,625
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
1750011
Name
n4-highmem-8
Description
8 vCPUs, 64 GB RAM
Family
n4
Hw Virt
Average Time To Start
19
Status
active
Observed At
2026-09-03T14:15:25.653485

Availability

REGION / IDSPOTONDEMAND
Columbus (US) / us-east5
0.1533 USD/h 0.4761 USD/h
Ashburn (US) / us-east4
0.2693 USD/h 0.4761 USD/h
Council Bluffs (US) / us-central1
0.2844 USD/h 0.4761 USD/h
The Dalles (US) / us-west1
0.2844 USD/h 0.4761 USD/h
Moncks Corner (US) / us-east1
0.2844 USD/h 0.4761 USD/h
Delhi (IN) / asia-south2
0.1267 USD/h 0.4951 USD/h
Mumbai (IN) / asia-south1
0.1543 USD/h 0.4951 USD/h
Eemshaven (NL) / europe-west4
0.1172 USD/h 0.4999 USD/h
Bangkok (TH) / asia-southeast3
0.1229 USD/h 0.4999 USD/h
Stockholm (SE) / europe-north2
0.2076 USD/h 0.4999 USD/h
Queretaro (MX) / northamerica-south1
0.2208 USD/h 0.5189 USD/h
Tel Aviv (IL) / me-west1
0.1701 USD/h 0.5237 USD/h
St. Ghislain (BE) / europe-west1
0.0845 USD/h 0.5242 USD/h
Montréal (CA) / northamerica-northeast1
0.1098 USD/h 0.5242 USD/h
Johannesburg (ZA) / africa-south1
0.1258 USD/h 0.5242 USD/h
Toronto (CA) / northamerica-northeast2
0.1774 USD/h 0.5242 USD/h
Hamina (FI) / europe-north1
0.2411 USD/h 0.5242 USD/h
Las Vegas (US) / us-west4
0.2775 USD/h 0.5362 USD/h
London (GB) / europe-west2
0.2003 USD/h 0.5427 USD/h
Changhua County (TW) / asia-east1
0.2096 USD/h 0.5513 USD/h
Milan (IT) / europe-west8
0.127 USD/h 0.5523 USD/h
Paris (FR) / europe-west9
0.1641 USD/h 0.5523 USD/h
Dallas (US) / us-south1
0.1161 USD/h 0.5618 USD/h
Madrid (ES) / europe-southwest1
0.1279 USD/h 0.5618 USD/h
Frankfurt (DE) / europe-west3
0.3202 USD/h 0.5618 USD/h
Salt Lake City (US) / us-west3
0.0922 USD/h 0.5723 USD/h
Los Angeles (US) / us-west2
0.3111 USD/h 0.5723 USD/h
Warsaw (PL) / europe-central2
0.2546 USD/h 0.5761 USD/h
Doha (QA) / me-central1
0.2534 USD/h 0.5784 USD/h
Jurong West (SG) / asia-southeast1
0.2923 USD/h 0.5873 USD/h
Sydney (AU) / australia-southeast1
0.2745 USD/h 0.5951 USD/h
Osaka (JP) / asia-northeast2
0.2248 USD/h 0.6114 USD/h
Seoul (KR) / asia-northeast3
0.307 USD/h 0.6114 USD/h
Tokyo (JP) / asia-northeast1
0.3344 USD/h 0.6114 USD/h
Melbourne (AU) / australia-southeast2
0.1897 USD/h 0.6189 USD/h
Zurich (CH) / europe-west6
0.2758 USD/h 0.6237 USD/h
Jakarta (ID) / asia-southeast2
0.1856 USD/h 0.6402 USD/h
Hong Kong / asia-east2
0.0779 USD/h 0.666 USD/h
Santiago (CL) / southamerica-west1
0.2002 USD/h 0.6808 USD/h
Osasco (BR) / southamerica-east1
0.1295 USD/h 0.756 USD/h
Dammam (SA) / me-central2
0.1469 USD/h 0.7617 USD/h

Processor

vCPUs
8
CPU Allocation
Dedicated
CPU Cores
4
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU L1D Cache
48 KiB
CPU L1D Cache Total
192 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
128 KiB
CPU L2 Cache
2 MiB
CPU L2 Cache Total
8 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
4.2
Scalability
105

System Resources and Accelerators

MEMORY
Memory Amount
64 GiB
Memory Amount Actual
64 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

      An Intel-powered virtual machine offering high memory density and advanced matrix extensions for memory-bound workloads and database caching.

      Memory OptimizedGeneral Purpose

      Google Cloud Platform n4-highmem-8 is a memory-optimized virtual machine featuring 8 vCPUs and 64.0 GB of RAM, powered by an Intel x86_64 architecture with 4 physical cores and dedicated CPU allocation. It lacks local storage and GPU accelerators. The processor includes a 260 MB L3 cache and supports advanced instruction sets like AVX-512 and AMX. Performance benchmarks place this instance in the average tier for most tasks, with a Geekbench multi-core score of 6984.0 and Redis SET throughput of 9.89 million operations per second. However, it exhibits weaker performance in multi-threaded bzip3 decompression and medium-model LLM text generation. Qualitatively, its high memory-to-vCPU ratio offers efficient resource density for memory-intensive tasks without the cost of excess compute cores. This instance is suited for database operations, in-memory caching, and web serving.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      0.743Score
      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) 1,291,240 ops/sec 1,917,397 ops/sec 0.673 50.00% 50.00% -18.00%
      Redis RPS (pipeline=16, SET) 6,723,647 ops/sec 11,681,410 ops/sec 0.576 20.00% 20.00% -10.40%
      PassMark Memory Mark (composite) 2,195 2,418 0.908 10.00% 10.00% -0.96%
      Memory bandwidth (read, 16 MB ~ L3) 117,559 MB/sec 108,140 MB/sec 1.09 10.00% 10.00% +0.87%
      PassMark single-thread CPU 2,672 Mops/s 2,365 Mops/s 1.13 10.00% 10.00% +1.23%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,815

      Geekbench Multi-Core

      Score: 6,984

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 13039
      Compression
      		 131965
      Encryption
      		 7638
      Extended Instructions
      		 10215
      Floating Point Maths
      		 24665
      Integer Maths
      		 34553
      Physics
      		 1658
      Prime Numbers
      		 71
      Single Threaded
      		 2672
      String Sorting
      		 17906

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2195
      Database Operations
      		 4892
      Memory Latency
      		 59
      Memory Read Cached
      		 23632
      Memory Read Uncached
      		 8076
      Memory Write
      		 8001

      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-8 FAQs