m2-hypermem-416 by Google Cloud Platform

m2-hypermem-416 is a 416 vCPUs, 8.625 TB RAM server offered by Google Cloud Platform with 416 vCPUs, 8832 GiB of memory and 0 GB of storage. The pricing starts at 67.2576 USD per hour.
416 vCPU
8832 GiB Memory
Spare SCore
370,889
(All-cores)
1,353
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
804417
Name
m2-hypermem-416
Description
416 vCPUs, 8.625 TB RAM
Family
m2
Hw Virt
Average Time To Start
36.4
Status
active
Observed At
2026-10-31T08:44:47.764832

Availability

REGION / IDSPOTONDEMAND
Council Bluffs (US) / us-central1
- 67.2576 USD/h
Montréal (CA) / northamerica-northeast1
- 70.7073 USD/h
Eemshaven (NL) / europe-west4
- 70.7112 USD/h
Toronto (CA) / northamerica-northeast2
- 73.9834 USD/h
St. Ghislain (BE) / europe-west1
- 74.1568 USD/h
Ashburn (US) / us-east4
- 75.9183 USD/h
Las Vegas (US) / us-west4
- 75.92 USD/h
Delhi (IN) / asia-south2
- 77.1231 USD/h
Mumbai (IN) / asia-south1
- 77.1333 USD/h
Milan (IT) / europe-west8
- 78.0188 USD/h
Jurong West (SG) / asia-southeast1
- 79.2085 USD/h
Madrid (ES) / europe-southwest1
- 79.364 USD/h
Tokyo (JP) / asia-northeast1
- 82.2291 USD/h
Osaka (JP) / asia-northeast2
- 82.2318 USD/h
Seoul (KR) / asia-northeast3
- 82.2318 USD/h
London (GB) / europe-west2
- 82.67 USD/h
Frankfurt (DE) / europe-west3
- 82.67 USD/h
Sydney (AU) / australia-southeast1
- 91.1299 USD/h
Santiago (CL) / southamerica-west1
- 96.1784 USD/h
Osasco (BR) / southamerica-east1
- 101.6204 USD/h
Dammam (SA) / me-central2
- 107.6122 USD/h

Processor

vCPUs
416
CPU Allocation
Dedicated
CPU Cores
208
CPU Speed
2.7 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU L1D Cache
32 KiB
CPU L1D Cache Total
7 MiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
7 MiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
208 MiB
CPU L3 Cache
39 MiB
CPU L3 Cache Total
308 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, monitor, vmx, ssse3, fma, cx16, pcid, sse4_1, sse4_2, x2apic, movbe, popcnt, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, abm, 3dnowprefetch, invpcid_single, ssbd, ibrs, ibpb, stibp, ibrs_enhanced, tpr_shadow, vnmi, flexpriority, ept, vpid, ept_ad, 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, avx512_vnni, md_clear, arch_capabilities
Ecpus
274.1
Scalability
65.89

System Resources and Accelerators

MEMORY
Memory Amount
9 TB
Memory Amount Actual
9 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 massive memory-optimized instance featuring 8.625 TB of RAM and 416 vCPUs for large-scale in-memory database workloads.

      Memory OptimizedGeneral Purpose

      Google Cloud Platform m2-hypermem-416 is a memory-optimized server featuring 416 vCPUs and 8.625 TB of RAM. It lacks local storage and GPUs. While single-core benchmarks like stress-ng and Geekbench single-core fall in the bottom 25%, its multi-core capabilities are in the top 10%, as demonstrated by stress-ng multi-core and Passmark CPU scores. Memory bandwidth is exceptionally strong, with both cached and uncached read/write operations ranking in the top 10%. This instance is designed for massive in-memory databases and heavy multi-threaded data processing, though it exhibits weak single-threaded efficiency and poor LLM text generation speeds.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      6.3Score
      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) 22,960,420 ops/sec 1,918,343 ops/sec 12 50.00% 50.00% +250.00%
      Redis RPS (pipeline=16, SET) 155,099,563 ops/sec 11,704,734 ops/sec 13 20.00% 20.00% +67.00%
      PassMark Memory Mark (composite) 1,298 2,416 0.54 10.00% 10.00% -6.00%
      Memory bandwidth (read, 16 MB ~ L3) 653,362 MB/sec 108,466 MB/sec 5.9 10.00% 10.00% +19.00%
      PassMark single-thread CPU 1,936 Mops/s 2,365 Mops/s 0.79 10.00% 10.00% -2.30%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,014

      Geekbench Multi-Core

      Score: 8,540

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 101,523
      Compression
      		 4,836,695
      Encryption
      		 132,486
      Extended Instructions
      		 335,026
      Floating Point Maths
      		 624,726
      Integer Maths
      		 1,176,653
      Physics
      		 16,399
      Prime Numbers
      		 1,157
      Single Threaded
      		 1,936
      String Sorting
      		 548,059

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 1,298
      Database Operations
      		 14,851
      Memory Latency
      		 73
      Memory Read Cached
      		 22,599
      Memory Read Uncached
      		 2,805
      Memory Write
      		 2,954

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 215.76 53.67 0.25×
      bitops
      		 104,974 24,936,889 237.55×
      branch
      		 149,435 46,156,306 308.87×
      funccall
      		 526.15 109,315 207.76×
      funcret
      		 10,923 3,002,328 274.86×
      hash
      		 122,329 35,447,037 289.77×
      intmath
      		 21,755 6,282,876 288.81×
      nop
      		 185,352 32,235,647 173.92×
      prime
      		 305,683 67,843,319 221.94×
      rotate
      		 93,768 26,224,764 279.68×
      str
      		 710,969 146,739,921 206.39×
      wcs
      		 456,439 93,501,998 204.85×
      CryptographySingleMultiScaling
      crypt
      		 2,366 452,257 191.18×
      CompressionSingleMultiScaling
      jpeg
      		 576.02 109,825 190.66×
      zlib
      		 47.57 15,888 333.99×
      HypervisorSingleMultiScaling
      clock
      		 6,215 47,815 7.69×
      clone
      		 924.88 23,164 25.05×
      context
      		 2,536 525,868 207.35×
      cpu-sched
      		 55.75 20,461 367.02×
      eventfd
      		 95,190 1,386,044 14.56×
      fault
      		 14,260 50,975 3.57×
      fork
      		 3,631 16,401 4.52×
      getrandom
      		 41,987 10,599,133 252.44×
      hrtimers
      		 229,822 8,764,744 38.14×
      mprotect
      		 311,803 10,764,152 34.52×
      mtx
      		 11,112,315 8,629,194,691 776.54×
      munmap
      		 3,054 24,488 8.02×
      null
      		 264,858 51,082,593 192.87×
      pipe
      		 312,981 107,536,727 343.59×
      priv-instr
      		 539,543 8,204,913 15.21×
      resched
      		 2,020,843 22,138,153 10.95×
      switch
      		 244,464 2,674,348 10.94×
      timermix
      		 186,168 41,854,880 224.82×
      tlb-shootdown
      		 4,904 52,726 10.75×
      tsc
      		 965,953 248,028,925 256.77×
      usersyscall
      		 380,198 7,051,497 18.55×
      vdso
      		 81,182,794 20,775,879,816 255.91×
      vfork
      		 23,516 27,211 1.16×
      x86syscall
      		 3,292,011 558,726,495 169.72×
      yield
      		 157,213,017 327,032,344 2.08×
      zero
      		 2,175,897 474,608,418 218.12×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 15,633 3,430,786 219.45×
      expmath
      		 2,592 752,767 290.39×
      fma
      		 547,965 178,461,943 325.68×
      fp
      		 127.08 30,482 239.87×
      fractal
      		 4.8 1,359 283.06×
      hyperbolic
      		 2,700 819,736 303.64×
      logmath
      		 4,393 1,222,280 278.23×
      matrix
      		 2,928 910,080 310.87×
      matrix-3d
      		 675.73 19,200 28.41×
      monte-carlo
      		 129.54 28,822 222.50×
      mpfr
      		 1,176 252,906 215.07×
      powmath
      		 1,535 453,761 295.57×
      trig
      		 1,656 414,735 250.42×
      veccmp
      		 15,080 3,003,638 199.18×
      vecfp
      		 1,276 322,544 252.79×
      vecmath
      		 2,121 639,661 301.56×
      vecshuf
      		 547.09 114,965 210.14×
      vecwide
      		 24,435 5,053,061 206.80×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 7 1,560 222.89×
      bsearch
      		 233.7 52,822 226.02×
      bubblesort
      		 0.6 129.4 215.67×
      fibsearch
      		 237.18 54,682 230.55×
      heapsort
      		 8.4 2,035 242.29×
      hsearch
      		 4,870 1,188,994 244.16×
      insertionsort
      		 8 1,587 198.37×
      malloc
      		 1,858,846 55,543,230 29.88×
      mcontend
      		 39.96 134,831 3374.14×
      mergesort
      		 22.6 5,390 238.51×
      qsort
      		 14.4 3,142 218.22×
      skiplist
      		 4,725 1,328,775 281.20×
      tree
      		 1.6 164 102.50×
      MemorySingleMultiScaling
      cache
      		 73,634 870,398 11.82×
      cachehammer
      		 197,530 5,141,201 26.03×
      cacheline
      		 7.54 - -
      l1cache
      		 218.79 - -
      memcpy
      		 336.72 69,588 206.66×
      memrate
      		 0.58 40.5 69.83×
      memthrash
      		 243.83 1,148 4.71×
      ptr-chase
      		 48,622,802 2,458,442,096 50.56×
      spinmem
      		 210.79 - -
      stream
      		 1.24 10.56 8.52×
      vm
      		 30,621 - -

      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
      m2-ultramem-208 2085888 GiB0
      m2-megamem-416 4165888 GiB0
      m2-ultramem-416 41611776 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      m2-hypermem-416 FAQs