m3-megamem-64 by Google Cloud Platform

m3-megamem-64 is a 64 vCPUs, 976 GB RAM server offered by Google Cloud Platform with 64 vCPUs, 976 GiB of memory and 0 GB of storage. The pricing starts at 0.6771 USD per hour.
64 vCPU
976 GiB Memory
Spare SCore
60,167
(All-cores)
1,852
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
1400064
Name
m3-megamem-64
Description
64 vCPUs, 976 GB RAM
Family
m3
Hw Virt
Average Time To Start
19.33
Status
active
Observed At
2026-11-07T00:35:37.912614

Availability

REGION / IDSPOTONDEMAND
Ashburn (US) / us-east4
1.2008 USD/h 7.1812 USD/h
Council Bluffs (US) / us-central1
3.3276 USD/h 7.2048 USD/h
The Dalles (US) / us-west1
3.3276 USD/h 7.2048 USD/h
Moncks Corner (US) / us-east1
3.3276 USD/h 7.2048 USD/h
Mumbai (IN) / asia-south1
0.7826 USD/h 7.4999 USD/h
Delhi (IN) / asia-south2
0.6771 USD/h 7.5002 USD/h
Bangkok (TH) / asia-southeast3
3.0946 USD/h 7.5699 USD/h
Eemshaven (NL) / europe-west4
0.8244 USD/h 7.5726 USD/h
Tel Aviv (IL) / me-west1
1.6047 USD/h 7.9253 USD/h
Hamina (FI) / europe-north1
0.7137 USD/h 7.9332 USD/h
Toronto (CA) / northamerica-northeast2
0.7137 USD/h 7.9332 USD/h
Montréal (CA) / northamerica-northeast1
0.7169 USD/h 7.9332 USD/h
St. Ghislain (BE) / europe-west1
1.5148 USD/h 7.9332 USD/h
Johannesburg (ZA) / africa-south1
1.5507 USD/h 7.9332 USD/h
Las Vegas (US) / us-west4
0.8422 USD/h 8.1148 USD/h
London (GB) / europe-west2
0.7389 USD/h 8.2033 USD/h
Changhua County (TW) / asia-east1
0.7574 USD/h 8.3424 USD/h
Paris (FR) / europe-west9
0.7525 USD/h 8.3576 USD/h
Milan (IT) / europe-west8
0.7535 USD/h 8.3576 USD/h
Frankfurt (DE) / europe-west3
0.8027 USD/h 8.4911 USD/h
Madrid (ES) / europe-southwest1
0.7664 USD/h 8.5017 USD/h
Salt Lake City (US) / us-west3
1.3118 USD/h 8.6609 USD/h
Warsaw (PL) / europe-central2
2.4058 USD/h 8.7174 USD/h
Doha (QA) / me-central1
1.4358 USD/h 8.7538 USD/h
Jurong West (SG) / asia-southeast1
0.8007 USD/h 8.8886 USD/h
Sydney (AU) / australia-southeast1
0.8111 USD/h 9.0028 USD/h
Osaka (JP) / asia-northeast2
0.8321 USD/h 9.2524 USD/h
Tokyo (JP) / asia-northeast1
0.9153 USD/h 9.2524 USD/h
Seoul (KR) / asia-northeast3
2.7505 USD/h 9.2524 USD/h
Turin (IT) / europe-west12
0.8415 USD/h 9.2942 USD/h
Melbourne (AU) / australia-southeast2
1.6785 USD/h 9.3629 USD/h
Zurich (CH) / europe-west6
0.8496 USD/h 9.4388 USD/h
Santiago (CL) / southamerica-west1
0.927 USD/h 10.3029 USD/h
Osasco (BR) / southamerica-east1
1.0325 USD/h 11.4405 USD/h
Dammam (SA) / me-central2
1.0454 USD/h 11.5277 USD/h

Processor

vCPUs
64
CPU Allocation
Dedicated
CPU Cores
32
CPU Speed
2.6 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
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
1 MiB
CPU L2 Cache Total
40 MiB
CPU L3 Cache
54 MiB
CPU L3 Cache Total
54 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, vmx, ssse3, fma, cx16, pcid, sse4_1, sse4_2, x2apic, movbe, popcnt, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, abm, 3dnowprefetch, ssbd, ibrs, ibpb, stibp, ibrs_enhanced, tpr_shadow, flexpriority, ept, vpid, ept_ad, 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, arat, vnmi, avx512vbmi, umip, avx512_vbmi2, gfni, vaes, vpclmulqdq, avx512_vnni, avx512_bitalg, avx512_vpopcntdq, rdpid, fsrm, md_clear, arch_capabilities
Ecpus
32.5
Scalability
50.78

System Resources and Accelerators

MEMORY
Memory Amount
976 GiB
Memory Amount Actual
976 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 instance with 64 vCPUs and 976 GB RAM designed for large-scale database operations and memory-bound parallel workloads.

      Memory OptimizedStorage & Database

      Google Cloud Platform m3-megamem-64 is a memory-optimized cloud server built on 32 physical Intel Xeon cores operating at 2.6 GHz, providing 64 dedicated vCPUs and 976 GB of system RAM. With 15.25 GB of RAM per vCPU, 54 MB of L3 cache, and support for AVX-512 and VAES instruction sets, the instance delivers high memory density without bundled local storage or GPUs. Benchmark testing reveals strong performance in multi-core tasks, including PassMark database operations, Geekbench multi-core scoring, software compilation with Clang, ray tracing, and multi-threaded bzip3 decompression. Single-threaded metrics and uncached memory bandwidth fall into the average range for its hardware tier. The instance represents a resource-dense deployment option for workloads where memory capacity and concurrent execution are critical, making it well-matched for large in-memory caching systems, database management systems, batch data processing, and enterprise software backends.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      2.4Score
      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) 6,558,191 ops/sec 1,936,298 ops/sec 3.5 50.00% 50.00% +87.00%
      Redis RPS (pipeline=16, SET) 35,079,213 ops/sec 11,797,257 ops/sec 2.9 20.00% 20.00% +24.00%
      PassMark Memory Mark (composite) 2,676 2,407 1.1 10.00% 10.00% +0.96%
      Memory bandwidth (read, 16 MB ~ L3) 159,006 MB/sec 108,490 MB/sec 1.5 10.00% 10.00% +4.10%
      PassMark single-thread CPU 2,296 Mops/s 2,365 Mops/s 0.96 10.00% 10.00% -0.41%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,577

      Geekbench Multi-Core

      Score: 16,654

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 54,571
      Compression
      		 898,007
      Encryption
      		 52,571
      Extended Instructions
      		 50,816
      Floating Point Maths
      		 133,312
      Integer Maths
      		 260,577
      Physics
      		 3,711
      Prime Numbers
      		 256
      Single Threaded
      		 2,296
      String Sorting
      		 114,897

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2,676
      Database Operations
      		 26,047
      Memory Latency
      		 56
      Memory Read Cached
      		 23,565
      Memory Read Uncached
      		 11,245
      Memory Write
      		 10,669

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 242.92 258.29 1.06×
      bitops
      		 126,777 4,120,904 32.51×
      branch
      		 133,611 6,773,328 50.69×
      funccall
      		 617.96 19,081 30.88×
      funcret
      		 11,538 489,666 42.44×
      hash
      		 147,824 6,730,333 45.53×
      intmath
      		 59,317 2,325,181 39.20×
      nop
      		 183,025 5,118,492 27.97×
      prime
      		 384,035 12,470,317 32.47×
      rotate
      		 95,159 3,231,946 33.96×
      str
      		 866,289 25,916,740 29.92×
      wcs
      		 585,912 15,537,087 26.52×
      CryptographySingleMultiScaling
      crypt
      		 2,767 79,150 28.61×
      CompressionSingleMultiScaling
      jpeg
      		 691.95 25,471 36.81×
      zlib
      		 37.99 2,478 65.23×
      HypervisorSingleMultiScaling
      clock
      		 37,769 491,080 13.00×
      clone
      		 464.83 5,787 12.45×
      context
      		 4,675 225,032 48.13×
      cpu-sched
      		 64.92 4,141 63.79×
      eventfd
      		 60,331 1,790,805 29.68×
      fault
      		 17,521 336,731 19.22×
      fork
      		 5,825 113,906 19.55×
      getrandom
      		 48,146 1,694,528 35.20×
      hrtimers
      		 127,719 8,386,986 65.67×
      mprotect
      		 1,312,967 14,634,692 11.15×
      mtx
      		 13,121,039 1,903,771,492 145.09×
      munmap
      		 4,075 101,730 24.97×
      null
      		 733,271 29,056,757 39.63×
      pipe
      		 887,310 41,453,008 46.72×
      priv-instr
      		 745,567 19,160,677 25.70×
      resched
      		 14,716,354 6,192,949 0.42×
      switch
      		 97,609 13,974,866 143.17×
      timermix
      		 208,568 10,241,481 49.10×
      tlb-shootdown
      		 12,382 77,925 6.29×
      tsc
      		 746,906 35,034,170 46.91×
      usersyscall
      		 626,122 16,481,979 26.32×
      vdso
      		 103,673,762 3,519,136,604 33.94×
      vfork
      		 34,605 287,434 8.31×
      x86syscall
      		 8,322,352 371,247,815 44.61×
      yield
      		 44,584,783 59,894,459 1.34×
      zero
      		 4,404,898 160,286,448 36.39×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 14,416 523,818 36.34×
      expmath
      		 2,810 125,204 44.55×
      fma
      		 619,162 34,132,191 55.13×
      fp
      		 148.8 6,144 41.29×
      fractal
      		 4.8 221.12 46.07×
      hyperbolic
      		 2,989 136,780 45.76×
      logmath
      		 4,725 212,013 44.87×
      matrix
      		 3,403 147,120 43.23×
      matrix-3d
      		 766.55 5,732 7.48×
      monte-carlo
      		 246.99 10,284 41.64×
      mpfr
      		 1,375 43,430 31.58×
      powmath
      		 1,642 74,518 45.38×
      trig
      		 1,923 71,423 37.14×
      veccmp
      		 19,804 569,436 28.75×
      vecfp
      		 1,486 56,791 38.22×
      vecmath
      		 3,144 135,281 43.03×
      vecshuf
      		 647.9 21,775 33.61×
      vecwide
      		 30,634 991,647 32.37×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 7.8 231.59 29.69×
      bsearch
      		 240.99 9,825 40.77×
      bubblesort
      		 1 25.6 25.60×
      fibsearch
      		 280.84 11,037 39.30×
      heapsort
      		 9.2 319.99 34.78×
      hsearch
      		 6,939 231,538 33.37×
      insertionsort
      		 10.2 192 18.82×
      malloc
      		 2,735,134 62,281,233 22.77×
      mcontend
      		 110.47 12,995 117.64×
      mergesort
      		 26 1,028 39.55×
      qsort
      		 20.2 618.58 30.62×
      skiplist
      		 5,291 238,131 45.01×
      tree
      		 1.6 38.33 23.96×
      MemorySingleMultiScaling
      cache
      		 393,196 1,094,650 2.78×
      cachehammer
      		 371,649 15,025,177 40.43×
      cacheline
      		 71.76 4,184 58.31×
      l1cache
      		 875.97 11,667 13.32×
      memcpy
      		 396.17 11,570 29.21×
      memrate
      		 1.58 23.18 14.67×
      memthrash
      		 282.98 1,211 4.28×
      ptr-chase
      		 34,397,219 512,392,872 14.90×
      spinmem
      		 223.79 3,021 13.50×
      stream
      		 34.6 19,055 550.73×
      vm
      		 108,729 303,493 2.79×

      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
      m3-ultramem-32 32976 GiB0
      m3-ultramem-64 641952 GiB0
      m3-megamem-128 1281952 GiB0
      m3-ultramem-128 1283904 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      m3-megamem-64 FAQs