e2-highmem-8 by Google Cloud Platform

e2-highmem-8 is a Efficient Instance, 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 0.0563 USD per hour.
8 vCPU
64 GiB Memory
Spare SCore
10,764
(All-cores)
2,681
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
336008
Name
e2-highmem-8
Description
Efficient Instance, 8 vCPUs, 64 GB RAM
Family
e2
Hw Virt
Average Time To Start
19
Status
active
Observed At
2026-11-01T09:19:14.326556

Availability

REGION / IDSPOTONDEMAND
Columbus (US) / us-east5
0.2014 USD/h 0.3616 USD/h
Council Bluffs (US) / us-central1
0.217 USD/h 0.3616 USD/h
The Dalles (US) / us-west1
0.217 USD/h 0.3616 USD/h
Moncks Corner (US) / us-east1
0.217 USD/h 0.3616 USD/h
Stockholm (SE) / europe-north2
0.1067 USD/h 0.3797 USD/h
Queretaro (MX) / northamerica-south1
0.1349 USD/h 0.3941 USD/h
Johannesburg (ZA) / africa-south1
0.1336 USD/h 0.3978 USD/h
St. Ghislain (BE) / europe-west1
0.1938 USD/h 0.3978 USD/h
Tel Aviv (IL) / me-west1
0.2247 USD/h 0.3978 USD/h
Toronto (CA) / northamerica-northeast2
0.0825 USD/h 0.3981 USD/h
Hamina (FI) / europe-north1
0.1148 USD/h 0.3981 USD/h
Montréal (CA) / northamerica-northeast1
0.1355 USD/h 0.3981 USD/h
Eemshaven (NL) / europe-west4
0.2269 USD/h 0.3981 USD/h
Las Vegas (US) / us-west4
0.0563 USD/h 0.4072 USD/h
Ashburn (US) / us-east4
0.2431 USD/h 0.4072 USD/h
Changhua County (TW) / asia-east1
0.2141 USD/h 0.4187 USD/h
Milan (IT) / europe-west8
0.2178 USD/h 0.4194 USD/h
Paris (FR) / europe-west9
0.2367 USD/h 0.4194 USD/h
Dallas (US) / us-south1
0.1422 USD/h 0.4267 USD/h
Madrid (ES) / europe-southwest1
0.1876 USD/h 0.4267 USD/h
Los Angeles (US) / us-west2
0.1311 USD/h 0.4343 USD/h
Salt Lake City (US) / us-west3
0.144 USD/h 0.4343 USD/h
Delhi (IN) / asia-south2
0.2129 USD/h 0.4343 USD/h
Mumbai (IN) / asia-south1
0.2605 USD/h 0.4343 USD/h
Melbourne (AU) / australia-southeast2
0.2256 USD/h 0.4361 USD/h
Warsaw (PL) / europe-central2
0.1926 USD/h 0.4375 USD/h
Doha (QA) / me-central1
0.2278 USD/h 0.4393 USD/h
Jurong West (SG) / asia-southeast1
0.2677 USD/h 0.4461 USD/h
Osaka (JP) / asia-northeast2
0.1459 USD/h 0.4635 USD/h
Seoul (KR) / asia-northeast3
0.2195 USD/h 0.4635 USD/h
Tokyo (JP) / asia-northeast1
0.2781 USD/h 0.4635 USD/h
Berlin (DE) / europe-west10
0.0892 USD/h 0.4659 USD/h
London (GB) / europe-west2
0.1854 USD/h 0.4659 USD/h
Frankfurt (DE) / europe-west3
0.2795 USD/h 0.4659 USD/h
Turin (IT) / europe-west12
0.1036 USD/h 0.4665 USD/h
Zurich (CH) / europe-west6
0.2114 USD/h 0.4737 USD/h
Jakarta (ID) / asia-southeast2
0.1108 USD/h 0.4862 USD/h
Hong Kong / asia-east2
0.1523 USD/h 0.5059 USD/h
Sydney (AU) / australia-southeast1
0.2863 USD/h 0.5131 USD/h
Santiago (CL) / southamerica-west1
0.2484 USD/h 0.5171 USD/h
Osasco (BR) / southamerica-east1
0.1195 USD/h 0.574 USD/h
Dammam (SA) / me-central2
0.3471 USD/h 0.5786 USD/h

Processor

vCPUs
8
CPU Allocation
Dedicated
CPU Cores
4
CPU Architecture
x86_64
CPU Manufacturer
AMD
CPU Family
EPYC
CPU Model
7B12
CPU L1D Cache
32 KiB
CPU L1D Cache Total
128 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
128 KiB
CPU L2 Cache
512 KiB
CPU L2 Cache Total
2 MiB
CPU L3 Cache
16 MiB
CPU L3 Cache Total
16 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, nonstop_tsc, cpuid, extd_apicid, tsc_known_freq, pni, pclmulqdq, ssse3, fma, cx16, 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, vmmcall, fsgsbase, tsc_adjust, bmi1, avx2, smep, bmi2, rdseed, adx, smap, clflushopt, clwb, sha_ni, xsaveopt, xsavec, xgetbv1, clzero, xsaveerptr, arat, npt, nrip_save, umip, rdpid
Ecpus
4
Scalability
50

System Resources and Accelerators

MEMORY
Memory Amount
64 GiB
Memory Amount Actual
64 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

      High-density memory virtual machine featuring dedicated AMD EPYC vCPUs, designed for memory-intensive cloud application workloads and caching layers.

      Memory OptimizedGeneral Purpose

      Google Cloud Platform e2-highmem-8 is a memory-optimized virtual machine powered by an AMD EPYC 7B12 CPU. Configured with 8 dedicated vCPUs across 4 physical cores and 64 GB of RAM, it maintains a 1:8 vCPU-to-memory ratio. It lacks attached local storage and GPUs. Benchmark results demonstrate strong single-core CPU performance alongside average multi-core processing, memory bandwidth, and database transaction capacity. Performance drops in specialized multi-threaded decompression and instruction set tests. The instance offers resource density for memory-intensive applications that require balanced compute overhead. Ideal workloads include in-memory databases, Redis caches, web servers with large memory footprints, and data processing jobs.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      0.43Score
      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) 592,717 ops/sec 1,918,343 ops/sec 0.31 50.00% 50.00% -44.00%
      Redis RPS (pipeline=16, SET) 4,322,278 ops/sec 11,704,734 ops/sec 0.36 20.00% 20.00% -18.00%
      PassMark Memory Mark (composite) 1,918 2,416 0.79 10.00% 10.00% -2.30%
      Memory bandwidth (read, 16 MB ~ L3) 88,235 MB/sec 108,466 MB/sec 0.8 10.00% 10.00% -2.20%
      PassMark single-thread CPU 2,285 Mops/s 2,365 Mops/s 0.96 10.00% 10.00% -0.41%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,458

      Geekbench Multi-Core

      Score: 5,778

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 10,537
      Compression
      		 109,718
      Encryption
      		 8,376
      Extended Instructions
      		 5,143
      Floating Point Maths
      		 18,210
      Integer Maths
      		 32,785
      Physics
      		 1,184
      Prime Numbers
      		 61
      Single Threaded
      		 2,285
      String Sorting
      		 16,245

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 1,918
      Database Operations
      		 3,001
      Memory Latency
      		 92
      Memory Read Cached
      		 18,615
      Memory Read Uncached
      		 12,592
      Memory Write
      		 12,415

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 694.16 281.17 0.41×
      bitops
      		 137,659 627,999 4.56×
      branch
      		 160,771 1,180,061 7.34×
      funccall
      		 531.19 2,744 5.17×
      funcret
      		 16,260 86,172 5.30×
      hash
      		 130,506 809,961 6.21×
      intmath
      		 57,398 302,032 5.26×
      nop
      		 279,355 1,127,550 4.04×
      prime
      		 376,196 1,862,850 4.95×
      rotate
      		 76,094 305,224 4.01×
      str
      		 828,065 3,990,917 4.82×
      wcs
      		 553,650 2,463,971 4.45×
      CryptographySingleMultiScaling
      crypt
      		 3,177 12,502 3.94×
      CompressionSingleMultiScaling
      jpeg
      		 669.17 3,891 5.81×
      zlib
      		 52.23 358.25 6.86×
      HypervisorSingleMultiScaling
      clock
      		 19,283 81,910 4.25×
      clone
      		 99.67 599.4 6.01×
      context
      		 3,501 23,141 6.61×
      cpu-sched
      		 66.85 508.26 7.60×
      eventfd
      		 29,152 260,965 8.95×
      fault
      		 7,300 39,793 5.45×
      fork
      		 1,325 11,746 8.87×
      getrandom
      		 43,173 218,897 5.07×
      hrtimers
      		 116,313 486,892 4.19×
      mprotect
      		 346,859 1,205,692 3.48×
      mtx
      		 44,669,514 425,592,763 9.53×
      munmap
      		 1,166 10,001 8.58×
      null
      		 443,140 2,782,940 6.28×
      pipe
      		 399,341 2,416,445 6.05×
      priv-instr
      		 368,998 2,176,748 5.90×
      resched
      		 1,371,012 329,905 0.24×
      switch
      		 42,919 1,061,681 24.74×
      timermix
      		 144,777 871,923 6.02×
      tlb-shootdown
      		 7,402 14,943 2.02×
      tsc
      		 650,759 4,997,476 7.68×
      usersyscall
      		 298,279 1,789,049 6.00×
      vdso
      		 77,876,717 506,282,813 6.50×
      vfork
      		 12,868 56,299 4.38×
      x86syscall
      		 5,661,430 35,561,605 6.28×
      yield
      		 3,692,350 3,534,007 0.96×
      zero
      		 2,547,906 14,730,497 5.78×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 13,905 58,698 4.22×
      expmath
      		 2,552 15,822 6.20×
      fma
      		 764,549 4,629,909 6.06×
      fp
      		 220.33 1,299 5.89×
      fractal
      		 6.6 43.2 6.55×
      hyperbolic
      		 3,214 19,495 6.06×
      logmath
      		 3,805 21,615 5.68×
      matrix
      		 2,636 16,247 6.16×
      matrix-3d
      		 462.91 2,176 4.70×
      monte-carlo
      		 204.19 1,277 6.25×
      mpfr
      		 1,352 6,766 5.01×
      powmath
      		 1,190 7,768 6.53×
      trig
      		 1,441 8,730 6.06×
      veccmp
      		 15,769 83,049 5.27×
      vecfp
      		 1,457 8,108 5.56×
      vecmath
      		 3,365 21,626 6.43×
      vecshuf
      		 526.76 2,445 4.64×
      vecwide
      		 23,394 119,296 5.10×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 8 32.8 4.10×
      bsearch
      		 260.31 1,307 5.02×
      bubblesort
      		 0.8 4.6 5.75×
      fibsearch
      		 309.5 1,402 4.53×
      heapsort
      		 9 44.19 4.91×
      hsearch
      		 7,298 34,066 4.67×
      insertionsort
      		 11.2 43.4 3.88×
      malloc
      		 985,398 7,837,465 7.95×
      mcontend
      		 80.51 956.88 11.89×
      mergesort
      		 26 154.59 5.95×
      qsort
      		 18.4 100.4 5.46×
      skiplist
      		 5,990 35,813 5.98×
      tree
      		 0.6 3.2 5.33×
      MemorySingleMultiScaling
      cache
      		 310,465 415,479 1.34×
      cachehammer
      		 121,057 1,137,768 9.40×
      cacheline
      		 30.85 264.77 8.58×
      l1cache
      		 150.15 631.36 4.20×
      memcpy
      		 343.28 1,316 3.83×
      memrate
      		 1.37 6.16 4.50×
      memthrash
      		 72.97 295.85 4.05×
      ptr-chase
      		 4,514,647 46,490,075 10.30×
      spinmem
      		 198.77 305.36 1.54×
      stream
      		 90.97 4,271 46.95×
      vm
      		 59,058 288,763 4.89×

      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

      Alternatives

      Servers of the Same Family

      INSTANCEvCPUsMEMORYAccelerators
      e2-micro 21 GiB0
      e2-small 22 GiB0
      e2-highcpu-2 22 GiB0
      e2-medium 24 GiB0
      e2-standard-2 28 GiB0
      e2-highmem-2 216 GiB0
      e2-highcpu-4 44 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      e2-highmem-8 FAQs