m3-ultramem-64 by Google Cloud Platform

m3-ultramem-64 is a 64 vCPUs, 1952 GB RAM server offered by Google Cloud Platform with 64 vCPUs, 1952 GiB of memory and 0 GB of storage. The pricing starts at 1.1456 USD per hour.
64 vCPU
1952 GiB Memory
Spare SCore
60,404
(All-cores)
1,845
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
1410064
Name
m3-ultramem-64
Description
64 vCPUs, 1952 GB RAM
Family
m3
Hw Virt
Average Time To Start
18
Status
active
Observed At
2026-11-05T22:18:35.554447

Availability

REGION / IDSPOTONDEMAND
Ashburn (US) / us-east4
2.0304 USD/h 12.1425 USD/h
Council Bluffs (US) / us-central1
5.6261 USD/h 12.1824 USD/h
The Dalles (US) / us-west1
5.6261 USD/h 12.1824 USD/h
Moncks Corner (US) / us-east1
5.6261 USD/h 12.1824 USD/h
Mumbai (IN) / asia-south1
1.3233 USD/h 12.6813 USD/h
Delhi (IN) / asia-south2
1.1456 USD/h 12.6818 USD/h
Bangkok (TH) / asia-southeast3
5.233 USD/h 12.8013 USD/h
Eemshaven (NL) / europe-west4
1.3934 USD/h 12.8043 USD/h
Tel Aviv (IL) / me-west1
2.7135 USD/h 13.4006 USD/h
Hamina (FI) / europe-north1
1.2066 USD/h 13.414 USD/h
Toronto (CA) / northamerica-northeast2
1.2066 USD/h 13.414 USD/h
Montréal (CA) / northamerica-northeast1
1.2117 USD/h 13.414 USD/h
St. Ghislain (BE) / europe-west1
2.561 USD/h 13.414 USD/h
Johannesburg (ZA) / africa-south1
2.6213 USD/h 13.414 USD/h
Las Vegas (US) / us-west4
1.4239 USD/h 13.721 USD/h
London (GB) / europe-west2
1.2494 USD/h 13.8707 USD/h
Changhua County (TW) / asia-east1
1.2805 USD/h 14.106 USD/h
Paris (FR) / europe-west9
1.2727 USD/h 14.1316 USD/h
Milan (IT) / europe-west8
1.2747 USD/h 14.1316 USD/h
Frankfurt (DE) / europe-west3
1.3571 USD/h 14.3574 USD/h
Madrid (ES) / europe-southwest1
1.2954 USD/h 14.3752 USD/h
Salt Lake City (US) / us-west3
2.2185 USD/h 14.6445 USD/h
Warsaw (PL) / europe-central2
4.0679 USD/h 14.7399 USD/h
Doha (QA) / me-central1
2.4274 USD/h 14.8016 USD/h
Jurong West (SG) / asia-southeast1
1.3532 USD/h 15.0294 USD/h
Sydney (AU) / australia-southeast1
1.3713 USD/h 15.2226 USD/h
Osaka (JP) / asia-northeast2
1.407 USD/h 15.6446 USD/h
Tokyo (JP) / asia-northeast1
1.5478 USD/h 15.6446 USD/h
Seoul (KR) / asia-northeast3
4.6518 USD/h 15.6446 USD/h
Turin (IT) / europe-west12
1.4232 USD/h 15.7153 USD/h
Melbourne (AU) / australia-southeast2
2.838 USD/h 15.8315 USD/h
Zurich (CH) / europe-west6
1.4362 USD/h 15.9598 USD/h
Santiago (CL) / southamerica-west1
1.5672 USD/h 17.4208 USD/h
Osasco (BR) / southamerica-east1
1.7469 USD/h 19.3444 USD/h
Dammam (SA) / me-central2
1.7677 USD/h 19.4918 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, 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, 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, avx512vbmi, umip, avx512_vbmi2, gfni, vaes, vpclmulqdq, avx512_vnni, avx512_bitalg, avx512_vpopcntdq, rdpid, fsrm, md_clear, arch_capabilities
Ecpus
32.7
Scalability
51.09

System Resources and Accelerators

MEMORY
Memory Amount
2 TB
Memory Amount Actual
2 TB
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

      Server Description

      A high-density memory-optimized instance featuring massive RAM capacity and strong multi-core performance for enterprise database workloads.

      Memory OptimizedStorage & Database

      Google Cloud Platform m3-ultramem-64 is a memory-optimized server featuring 64 dedicated vCPUs and 1952.0 GB of RAM, delivering a high memory-to-core ratio of 30.5 GB per vCPU. Powered by an Intel Xeon processor at 2.6 GHz on the x86_64 architecture, this instance includes a 54 MB L3 cache and supports AVX-512 instructions. It contains no local storage or GPUs. Benchmarks indicate strong multi-core performance, with a Passmark CPU score of 55325.27 and excellent database operation capabilities. The server is highly efficient for memory-intensive enterprise applications, large-scale in-memory databases, and complex software compilation tasks.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      2.6Score
      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) 7,580,701 ops/sec 1,936,298 ops/sec 4 50.00% 50.00% +100.00%
      Redis RPS (pipeline=16, SET) 36,788,283 ops/sec 11,797,257 ops/sec 3.1 20.00% 20.00% +25.00%
      PassMark Memory Mark (composite) 2,722 2,407 1.1 10.00% 10.00% +0.96%
      Memory bandwidth (read, 16 MB ~ L3) 160,464 MB/sec 108,490 MB/sec 1.5 10.00% 10.00% +4.10%
      PassMark single-thread CPU 2,356 Mops/s 2,365 Mops/s 1 10.00% 10.00% 0.00%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,584

      Geekbench Multi-Core

      Score: 16,753

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 55,325
      Compression
      		 898,887
      Encryption
      		 53,229
      Extended Instructions
      		 51,073
      Floating Point Maths
      		 133,844
      Integer Maths
      		 261,569
      Physics
      		 3,721
      Prime Numbers
      		 260
      Single Threaded
      		 2,356
      String Sorting
      		 117,924

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2,722
      Database Operations
      		 26,390
      Memory Latency
      		 55
      Memory Read Cached
      		 23,369
      Memory Read Uncached
      		 11,715
      Memory Write
      		 10,904

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 252.23 273.44 1.08×
      bitops
      		 126,807 4,126,990 32.55×
      branch
      		 133,664 6,774,771 50.69×
      funccall
      		 617.54 19,578 31.70×
      funcret
      		 11,385 504,344 44.30×
      hash
      		 146,933 6,806,113 46.32×
      intmath
      		 59,583 2,353,678 39.50×
      nop
      		 183,772 5,195,404 28.27×
      prime
      		 385,150 12,853,617 33.37×
      rotate
      		 95,153 3,239,167 34.04×
      str
      		 799,401 26,458,678 33.10×
      wcs
      		 594,008 15,973,542 26.89×
      CryptographySingleMultiScaling
      crypt
      		 2,766 81,309 29.40×
      CompressionSingleMultiScaling
      jpeg
      		 678.98 25,449 37.48×
      zlib
      		 47.36 2,690 56.81×
      HypervisorSingleMultiScaling
      clock
      		 38,214 499,419 13.07×
      clone
      		 472.34 5,776 12.23×
      context
      		 4,616 222,120 48.12×
      cpu-sched
      		 67.88 4,150 61.14×
      eventfd
      		 59,139 1,834,137 31.01×
      fault
      		 17,938 335,070 18.68×
      fork
      		 5,734 115,021 20.06×
      getrandom
      		 48,231 1,748,983 36.26×
      hrtimers
      		 536,878 7,956,925 14.82×
      mprotect
      		 1,310,217 14,673,352 11.20×
      mtx
      		 13,703,304 1,891,786,764 138.05×
      munmap
      		 4,150 102,299 24.65×
      null
      		 724,260 28,868,938 39.86×
      pipe
      		 926,940 34,924,256 37.68×
      priv-instr
      		 744,405 17,751,068 23.85×
      resched
      		 14,586,537 6,910,751 0.47×
      switch
      		 90,208 14,315,753 158.70×
      timermix
      		 209,624 10,523,988 50.20×
      tlb-shootdown
      		 10,804 91,621 8.48×
      tsc
      		 747,676 35,246,948 47.14×
      usersyscall
      		 623,780 15,551,521 24.93×
      vdso
      		 106,957,757 3,942,836,404 36.86×
      vfork
      		 34,112 195,888 5.74×
      x86syscall
      		 8,341,864 368,053,577 44.12×
      yield
      		 46,998,845 62,908,034 1.34×
      zero
      		 4,375,927 157,857,599 36.07×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 14,419 571,858 39.66×
      expmath
      		 2,810 129,475 46.08×
      fma
      		 620,632 34,456,662 55.52×
      fp
      		 174.52 6,344 36.35×
      fractal
      		 4.8 227.29 47.35×
      hyperbolic
      		 2,991 140,886 47.11×
      logmath
      		 4,720 217,505 46.08×
      matrix
      		 3,434 156,299 45.51×
      matrix-3d
      		 755.89 5,808 7.68×
      monte-carlo
      		 247.45 10,330 41.75×
      mpfr
      		 1,374 44,528 32.40×
      powmath
      		 1,642 76,406 46.53×
      trig
      		 1,916 73,100 38.16×
      veccmp
      		 19,798 586,771 29.64×
      vecfp
      		 1,486 57,721 38.84×
      vecmath
      		 3,146 139,684 44.41×
      vecshuf
      		 647.66 22,273 34.39×
      vecwide
      		 31,064 1,020,405 32.85×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 7.8 243.19 31.18×
      bsearch
      		 241.37 10,087 41.79×
      bubblesort
      		 1 25.6 25.60×
      fibsearch
      		 279.83 11,160 39.88×
      heapsort
      		 9.2 320.19 34.80×
      hsearch
      		 7,092 239,361 33.75×
      insertionsort
      		 10.2 192 18.82×
      malloc
      		 2,706,354 63,669,306 23.53×
      mcontend
      		 100.69 13,074 129.85×
      mergesort
      		 26.2 1,046 39.91×
      qsort
      		 20 633.78 31.69×
      skiplist
      		 5,289 244,446 46.22×
      tree
      		 1.6 38.33 23.96×
      MemorySingleMultiScaling
      cache
      		 420,317 1,111,512 2.64×
      cachehammer
      		 373,588 15,262,770 40.85×
      cacheline
      		 72.97 4,109 56.31×
      l1cache
      		 893.99 11,686 13.07×
      memcpy
      		 395.77 11,940 30.17×
      memrate
      		 1.78 23.24 13.06×
      memthrash
      		 303.26 1,224 4.04×
      ptr-chase
      		 35,112,665 514,912,738 14.66×
      spinmem
      		 222.79 2,973 13.34×
      stream
      		 35.42 19,418 548.23×
      vm
      		 108,730 303,566 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

      Alternatives

      Servers of the Same Family

      INSTANCEvCPUsMEMORYAccelerators
      m3-ultramem-32 32976 GiB0
      m3-megamem-64 64976 GiB0
      m3-megamem-128 1281952 GiB0
      m3-ultramem-128 1283904 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      m3-ultramem-64 FAQs