m1-megamem-96 by Google Cloud Platform

m1-megamem-96 is a 96 vCPUs, 1.4 TB RAM server offered by Google Cloud Platform with 96 vCPUs, 1434 GiB of memory and 0 GB of storage. The pricing starts at 1.0083 USD per hour.
96 vCPU
1434 GiB Memory
Spare SCore
70,553
(All-cores)
1,273
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
9196
Name
m1-megamem-96
Description
96 vCPUs, 1.4 TB RAM
Family
m1
Hw Virt
Average Time To Start
21
Status
active
Observed At
2026-11-03T13:23:09.417223

Availability

REGION / IDSPOTONDEMAND
Council Bluffs (US) / us-central1
1.4882 USD/h 10.6522 USD/h
The Dalles (US) / us-west1
1.4882 USD/h 10.6522 USD/h
Moncks Corner (US) / us-east1
1.4882 USD/h 10.6522 USD/h
Montréal (CA) / northamerica-northeast1
1.0083 USD/h 11.1973 USD/h
Eemshaven (NL) / europe-west4
1.305 USD/h 11.1979 USD/h
St. Ghislain (BE) / europe-west1
1.4772 USD/h 11.7432 USD/h
Las Vegas (US) / us-west4
1.0815 USD/h 12.0227 USD/h
Ashburn (US) / us-east4
1.9542 USD/h 12.0227 USD/h
Mumbai (IN) / asia-south1
1.1001 USD/h 12.2148 USD/h
Los Angeles (US) / us-west2
1.1001 USD/h 12.2168 USD/h
Changhua County (TW) / asia-east1
1.1198 USD/h 12.3622 USD/h
Jurong West (SG) / asia-southeast1
1.7763 USD/h 12.5422 USD/h
Tokyo (JP) / asia-northeast1
1.9538 USD/h 13.0266 USD/h
London (GB) / europe-west2
1.1772 USD/h 13.0918 USD/h
Frankfurt (DE) / europe-west3
1.1772 USD/h 13.0918 USD/h
Jakarta (ID) / asia-southeast2
1.2317 USD/h 13.6758 USD/h
Zurich (CH) / europe-west6
1.2552 USD/h 13.9531 USD/h
Osasco (BR) / southamerica-east1
1.4495 USD/h 16.0979 USD/h

Processor

vCPUs
96
CPU Allocation
Dedicated
CPU Cores
48
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU L1D Cache
32 KiB
CPU L1D Cache Total
2 MiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
2 MiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
48 MiB
CPU L3 Cache
39 MiB
CPU L3 Cache Total
77 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, pti, ssbd, ibrs, ibpb, stibp, fsgsbase, tsc_adjust, bmi1, hle, avx2, smep, bmi2, erms, invpcid, rtm, mpx, avx512f, avx512dq, rdseed, adx, smap, clflushopt, clwb, avx512cd, avx512bw, avx512vl, xsaveopt, xsavec, xgetbv1, xsaves, arat, md_clear, arch_capabilities
Ecpus
55.4
Scalability
57.71

System Resources and Accelerators

MEMORY
Memory Amount
1 TB
Memory Amount Actual
1 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

      CPU and System Topology

      Server Description

      A high-capacity memory-optimized platform featuring ninety-six dedicated vCPUs and over one terabyte of RAM for memory-intensive enterprise workloads.

      Memory Optimized

      Google Cloud Platform m1-megamem-96 is a memory-optimized instance featuring 96 dedicated vCPUs and 1434.0 GB of RAM, running on an Intel Xeon x86_64 architecture with 48 physical cores. The instance lacks bundled local storage and GPU accelerators. Performance benchmarks reveal a distinct tradeoff: single-core CPU performance is weak, ranking in the bottom 25%, whereas multi-core CPU performance and memory read bandwidth are strong, placing in the top 25%. Specifically, cached read bandwidth reaches 3918.5 GB/sec. This hardware profile is qualitatively optimized for high-density memory configurations rather than raw single-threaded speed. It is best suited for memory-intensive workloads, such as large in-memory databases, enterprise applications, and multi-threaded data processing tasks that require substantial memory capacity and high memory bandwidth.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      2Score
      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) 5,180,667 ops/sec 1,922,940 ops/sec 2.7 50.00% 50.00% +64.00%
      Redis RPS (pipeline=16, SET) 35,160,840 ops/sec 11,785,922 ops/sec 2.9 20.00% 20.00% +24.00%
      PassMark Memory Mark (composite) 2,125 2,415 0.88 10.00% 10.00% -1.30%
      Memory bandwidth (read, 16 MB ~ L3) 150,881 MB/sec 108,490 MB/sec 1.4 10.00% 10.00% +3.40%
      PassMark single-thread CPU 1,813 Mops/s 2,365 Mops/s 0.75 10.00% 10.00% -2.80%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,026

      Geekbench Multi-Core

      Score: 10,625

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 49,281
      Compression
      		 1,011,448
      Encryption
      		 30,963
      Extended Instructions
      		 63,076
      Floating Point Maths
      		 126,703
      Integer Maths
      		 235,875
      Physics
      		 4,776
      Prime Numbers
      		 297
      Single Threaded
      		 1,813
      String Sorting
      		 114,080

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2,125
      Database Operations
      		 18,852
      Memory Latency
      		 67
      Memory Read Cached
      		 21,994
      Memory Read Uncached
      		 7,432
      Memory Write
      		 7,430

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 237.2 92.49 0.39×
      bitops
      		 101,171 4,892,415 48.36×
      branch
      		 138,894 8,863,709 63.82×
      funccall
      		 488.98 21,232 43.42×
      funcret
      		 10,347 613,433 59.29×
      hash
      		 114,032 6,879,852 60.33×
      intmath
      		 20,320 1,260,851 62.05×
      nop
      		 172,514 6,269,179 36.34×
      prime
      		 285,266 13,545,531 47.48×
      rotate
      		 87,170 5,032,634 57.73×
      str
      		 680,256 27,926,109 41.05×
      wcs
      		 434,464 17,869,644 41.13×
      CryptographySingleMultiScaling
      crypt
      		 2,202 90,067 40.90×
      CompressionSingleMultiScaling
      jpeg
      		 510 24,927 48.88×
      zlib
      		 49.56 2,871 57.92×
      HypervisorSingleMultiScaling
      clock
      		 14,081 157,437 11.18×
      clone
      		 249.9 5,840 23.37×
      context
      		 1,133 60,532 53.45×
      cpu-sched
      		 73.42 6,087 82.90×
      eventfd
      		 39,037 1,382,753 35.42×
      fault
      		 8,231 132,930 16.15×
      fork
      		 2,615 54,643 20.90×
      getrandom
      		 38,328 2,001,286 52.21×
      hrtimers
      		 315,274 7,544,808 23.93×
      mprotect
      		 577,114 7,704,581 13.35×
      mtx
      		 12,954,176 1,656,818,721 127.90×
      munmap
      		 1,706 56,536 33.13×
      null
      		 110,313 5,717,916 51.83×
      pipe
      		 686,192 15,662,602 22.83×
      priv-instr
      		 288,070 8,287,753 28.77×
      resched
      		 3,295,006 3,668,383 1.11×
      switch
      		 89,862 9,003,576 100.19×
      timermix
      		 138,081 7,409,119 53.66×
      tlb-shootdown
      		 6,404 78,949 12.33×
      tsc
      		 898,390 52,615,258 58.57×
      usersyscall
      		 187,184 7,922,201 42.32×
      vdso
      		 74,416,666 4,321,772,108 58.08×
      vfork
      		 15,163 118,021 7.78×
      x86syscall
      		 1,235,584 64,513,529 52.21×
      yield
      		 27,352,043 28,960,301 1.06×
      zero
      		 950,775 50,295,469 52.90×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 14,587 718,241 49.24×
      expmath
      		 2,419 154,250 63.76×
      fma
      		 589,030 34,282,233 58.20×
      fp
      		 141.6 7,727 54.57×
      fractal
      		 4.8 291.61 60.75×
      hyperbolic
      		 2,515 165,237 65.69×
      logmath
      		 4,094 253,277 61.86×
      matrix
      		 2,715 174,570 64.30×
      matrix-3d
      		 608.97 5,892 9.68×
      monte-carlo
      		 63.99 3,754 58.66×
      mpfr
      		 1,092 48,560 44.46×
      powmath
      		 1,429 91,293 63.88×
      trig
      		 1,536 82,282 53.57×
      veccmp
      		 13,784 576,178 41.80×
      vecfp
      		 1,997 91,673 45.89×
      vecmath
      		 1,891 126,403 66.86×
      vecshuf
      		 826.61 34,157 41.32×
      vecwide
      		 49,953 2,245,937 44.96×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 6.4 306.99 47.97×
      bsearch
      		 218.38 10,767 49.30×
      bubblesort
      		 0.6 19.2 32.00×
      fibsearch
      		 218.7 10,670 48.79×
      heapsort
      		 7.8 384.79 49.33×
      hsearch
      		 4,547 228,923 50.34×
      insertionsort
      		 7.4 307 41.49×
      malloc
      		 1,900,540 54,294,964 28.57×
      mcontend
      		 58.91 11,196 190.06×
      mergesort
      		 21.2 1,105 52.10×
      qsort
      		 13.4 633.18 47.25×
      skiplist
      		 4,395 260,212 59.20×
      tree
      		 1.2 38.37 31.97×
      MemorySingleMultiScaling
      cache
      		 252,189 1,645,302 6.52×
      cachehammer
      		 321,240 11,479,535 35.74×
      cacheline
      		 15.36 1,398 91.02×
      l1cache
      		 204.37 8,789 43.01×
      memcpy
      		 314.09 13,905 44.27×
      memrate
      		 0.96 14.65 15.26×
      memthrash
      		 251.65 814.56 3.24×
      ptr-chase
      		 29,201,775 721,298,008 24.70×
      spinmem
      		 195.19 3,107 15.92×
      stream
      		 12.03 20,802 1729.20×
      vm
      		 29,767 308,184 10.35×

      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
      m1-ultramem-40 40961 GiB0
      m1-ultramem-80 801922 GiB0
      m1-ultramem-160 1603844 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      m1-megamem-96 FAQs