n1-highmem-4 by Google Cloud Platform

n1-highmem-4 is a 4 vCPUs, 26 GB RAM server offered by Google Cloud Platform with 4 vCPUs, 26 GiB of memory and 0 GB of storage. The pricing starts at 0.0362 USD per hour.
4 vCPU
26 GiB Memory
Spare SCore
2,914
(All-cores)
1,110
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
5004
Name
n1-highmem-4
Description
4 vCPUs, 26 GB RAM
Family
n1
Hw Virt
Average Time To Start
21.5
Status
active
Observed At
2026-10-28T23:53:37.887295

Availability

REGION / IDSPOTONDEMAND
Council Bluffs (US) / us-central1
0.1156 USD/h 0.2366 USD/h
The Dalles (US) / us-west1
0.1156 USD/h 0.2366 USD/h
Moncks Corner (US) / us-east1
0.1156 USD/h 0.2366 USD/h
St. Ghislain (BE) / europe-west1
0.1272 USD/h 0.2603 USD/h
Tel Aviv (IL) / me-west1
0.1503 USD/h 0.2603 USD/h
Hamina (FI) / europe-north1
0.0534 USD/h 0.2605 USD/h
Toronto (CA) / northamerica-northeast2
0.1137 USD/h 0.2605 USD/h
Montréal (CA) / northamerica-northeast1
0.1552 USD/h 0.2605 USD/h
Eemshaven (NL) / europe-west4
0.1559 USD/h 0.2605 USD/h
Las Vegas (US) / us-west4
0.1034 USD/h 0.2665 USD/h
Ashburn (US) / us-east4
0.1078 USD/h 0.2665 USD/h
Changhua County (TW) / asia-east1
0.0613 USD/h 0.274 USD/h
Delhi (IN) / asia-south2
0.0744 USD/h 0.2842 USD/h
Mumbai (IN) / asia-south1
0.0956 USD/h 0.2842 USD/h
Salt Lake City (US) / us-west3
0.1081 USD/h 0.2842 USD/h
Los Angeles (US) / us-west2
0.1238 USD/h 0.2842 USD/h
Warsaw (PL) / europe-central2
0.0888 USD/h 0.2863 USD/h
Jurong West (SG) / asia-southeast1
0.0733 USD/h 0.2919 USD/h
Tokyo (JP) / asia-northeast1
0.1208 USD/h 0.3034 USD/h
Osaka (JP) / asia-northeast2
0.1472 USD/h 0.3034 USD/h
Seoul (KR) / asia-northeast3
0.1556 USD/h 0.3034 USD/h
London (GB) / europe-west2
0.1087 USD/h 0.3048 USD/h
Frankfurt (DE) / europe-west3
0.1477 USD/h 0.3048 USD/h
Zurich (CH) / europe-west6
0.1228 USD/h 0.3099 USD/h
Jakarta (ID) / asia-southeast2
0.0362 USD/h 0.3181 USD/h
Hong Kong / asia-east2
0.049 USD/h 0.3311 USD/h
Melbourne (AU) / australia-southeast2
0.0599 USD/h 0.3357 USD/h
Sydney (AU) / australia-southeast1
0.1566 USD/h 0.3357 USD/h
Osasco (BR) / southamerica-east1
0.1189 USD/h 0.3756 USD/h

Processor

vCPUs
4
CPU Allocation
Dedicated
CPU Cores
2
CPU Speed
2.3 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU L1D Cache
32 KiB
CPU L1D Cache Total
64 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
64 KiB
CPU L2 Cache
256 KiB
CPU L2 Cache Total
512 KiB
CPU L3 Cache
45 MiB
CPU L3 Cache Total
45 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, pti, ssbd, ibrs, ibpb, stibp, fsgsbase, tsc_adjust, bmi1, avx2, smep, bmi2, erms, invpcid, xsaveopt, arat, md_clear, arch_capabilities
Ecpus
2.6
Scalability
65

System Resources and Accelerators

MEMORY
Memory Amount
26 GiB
Memory Amount Actual
26 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 server configuration delivering 26 GB of system RAM across 4 dedicated virtual CPUs for memory-intensive workloads.

      Memory Optimized

      Google Cloud Platform n1-highmem-4 is a memory-optimized instance featuring 4 dedicated x86_64 vCPUs powered by an Intel Xeon processor running at 2.3 GHz, supported by 26.0 GB of RAM. Driven by 2 physical cores with 2 threads per core and 45 MB of L3 cache, it delivers 6.5 GB of RAM per vCPU without bundled local storage or GPU accelerators. Benchmark evaluations reflect legacy performance levels, with single-core stress-ng at 1109.89 and Geekbench multi-core at 2032.0. Memory bandwidth measures 25.86 GB/sec on uncached 256MB reads, while Redis SET throughput reaches 2.75 million operations per second. The instance provides qualitative resource density for memory-bound applications that require substantial system memory relative to moderate compute demands, serving workloads such as caching nodes, light database instances, and general web applications.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      0.21Score
      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) 255,567 ops/sec 1,919,289 ops/sec 0.14 50.00% 50.00% -63.00%
      Redis RPS (pipeline=16, SET) 1,739,155 ops/sec 11,728,058 ops/sec 0.14 20.00% 20.00% -33.00%
      PassMark Memory Mark (composite) 1,763 2,416 0.75 10.00% 10.00% -2.80%
      Memory bandwidth (read, 16 MB ~ L3) 30,363 MB/sec 108,466 MB/sec 0.27 10.00% 10.00% -12.00%
      PassMark single-thread CPU 1,626 Mops/s 2,365 Mops/s 0.67 10.00% 10.00% -3.90%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 924

      Geekbench Multi-Core

      Score: 2,032

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 3,478
      Compression
      		 43,761
      Encryption
      		 1,343
      Extended Instructions
      		 2,368
      Floating Point Maths
      		 5,993
      Integer Maths
      		 9,732
      Physics
      		 446
      Prime Numbers
      		 21
      Single Threaded
      		 1,626
      String Sorting
      		 5,177

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 1,763
      Database Operations
      		 1,173
      Memory Latency
      		 68
      Memory Read Cached
      		 19,260
      Memory Read Uncached
      		 8,775
      Memory Write
      		 8,952

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 196.69 206.79 1.05×
      bitops
      		 84,496 193,754 2.29×
      branch
      		 120,974 361,956 2.99×
      funccall
      		 426.07 878.24 2.06×
      funcret
      		 8,917 25,273 2.83×
      hash
      		 98,977 283,465 2.86×
      intmath
      		 17,688 52,085 2.94×
      nop
      		 149,931 259,382 1.73×
      prime
      		 251,357 557,136 2.22×
      rotate
      		 76,138 207,878 2.73×
      str
      		 528,219 1,145,797 2.17×
      wcs
      		 361,284 752,464 2.08×
      CryptographySingleMultiScaling
      crypt
      		 1,897 3,702 1.95×
      CompressionSingleMultiScaling
      jpeg
      		 462.91 1,135 2.45×
      zlib
      		 39.93 114.3 2.86×
      HypervisorSingleMultiScaling
      clock
      		 15,339 40,645 2.65×
      clone
      		 258.97 445.47 1.72×
      context
      		 1,079 3,020 2.80×
      cpu-sched
      		 66.17 243.78 3.68×
      eventfd
      		 32,208 143,885 4.47×
      fault
      		 7,846 21,020 2.68×
      fork
      		 2,717 8,668 3.19×
      getrandom
      		 36,445 85,273 2.34×
      hrtimers
      		 194,751 317,532 1.63×
      mprotect
      		 372,543 392,114 1.05×
      mtx
      		 8,661,249 93,782,294 10.83×
      munmap
      		 1,879 5,476 2.91×
      null
      		 105,017 287,867 2.74×
      pipe
      		 633,884 898,820 1.42×
      priv-instr
      		 282,502 738,920 2.62×
      resched
      		 380,321 204,059 0.54×
      switch
      		 77,202 434,558 5.63×
      timermix
      		 139,367 355,880 2.55×
      tlb-shootdown
      		 6,505 7,666 1.18×
      tsc
      		 783,561 2,172,695 2.77×
      usersyscall
      		 187,188 488,191 2.61×
      vdso
      		 65,154,322 183,454,128 2.82×
      vfork
      		 21,645 54,303 2.51×
      x86syscall
      		 1,181,481 3,275,169 2.77×
      yield
      		 1,288,158 1,413,134 1.10×
      zero
      		 912,888 2,425,784 2.66×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 12,621 32,285 2.56×
      expmath
      		 2,112 6,402 3.03×
      fma
      		 506,297 1,633,956 3.23×
      fp
      		 93.01 241.23 2.59×
      fractal
      		 3.8 11.4 3.00×
      hyperbolic
      		 2,212 6,825 3.09×
      logmath
      		 3,559 10,447 2.94×
      matrix
      		 2,586 8,314 3.21×
      matrix-3d
      		 506.43 947.6 1.87×
      monte-carlo
      		 63 169.87 2.70×
      mpfr
      		 944.63 2,020 2.14×
      powmath
      		 1,249 3,787 3.03×
      trig
      		 1,346 3,532 2.62×
      veccmp
      		 12,213 25,640 2.10×
      vecfp
      		 1,096 2,767 2.52×
      vecmath
      		 1,751 5,379 3.07×
      vecshuf
      		 441.67 946.44 2.14×
      vecwide
      		 20,926 46,651 2.23×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 5.6 12.8 2.29×
      bsearch
      		 189.08 428.17 2.26×
      bubblesort
      		 0.6 0.8 1.33×
      fibsearch
      		 191.23 431.6 2.26×
      heapsort
      		 6.8 16 2.35×
      hsearch
      		 3,708 9,386 2.53×
      insertionsort
      		 6.4 12.8 2.00×
      malloc
      		 1,554,345 6,338,555 4.08×
      mcontend
      		 190.52 747.37 3.92×
      mergesort
      		 18.2 48.8 2.68×
      qsort
      		 11.6 26.4 2.28×
      skiplist
      		 3,838 10,701 2.79×
      tree
      		 1 2.4 2.40×
      MemorySingleMultiScaling
      cache
      		 264,325 290,377 1.10×
      cachehammer
      		 494,759 1,691,869 3.42×
      cacheline
      		 22.83 95.24 4.17×
      l1cache
      		 177.89 384.87 2.16×
      memcpy
      		 272.48 586.48 2.15×
      memrate
      		 1.16 2.45 2.11×
      memthrash
      		 43.77 143.79 3.29×
      ptr-chase
      		 11,788,706 40,804,968 3.46×
      spinmem
      		 79.6 60.79 0.76×
      stream
      		 20.91 200.09 9.57×
      vm
      		 16,780 203,852 12.15×

      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
      n1-standard-1 14 GiB0
      n1-highcpu-2 22 GiB0
      n1-standard-2 28 GiB0
      n1-highmem-2 213 GiB0
      n1-highcpu-4 44 GiB0
      n1-standard-4 415 GiB0
      n1-highcpu-8 87 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      n1-highmem-4 FAQs