M128-64ms by Microsoft Azure

M128-64ms is a MS family [Memory Intensive] [Premium Storage capable] [Intel processor] 128 vCPUs server offered by Microsoft Azure with 64 vCPUs, 3892 GiB of memory and 4.19 TB of storage. The pricing starts at 3.8698 USD per hour.
64 vCPU
3892 GiB Memory
4.19 TB Storage
Spare SCore
43,758
(All-cores)
1,039
(Single-core)

Specifications

Server Metadata

Vendor ID
azure
Server ID
Standard_M128-64ms
Name
M128-64ms
API Reference
Standard_M128-64ms
Description
MS family [Memory Intensive] [Premium Storage capable] [Intel processor] 128 vCPUs
Family
MS
Hw Virt
Average Time To Start
75
Status
active
Observed At
2026-10-24T11:47:00.103492

Availability

REGION / IDSPOTONDEMAND
East US (US) / eastus
4.9319 USD/h 26.688 USD/h
East US 2 (US) / eastus2
4.9319 USD/h 26.688 USD/h
North Central US (US) / northcentralus
4.9319 USD/h 26.688 USD/h
West US 2 (US) / westus2
4.9319 USD/h 26.688 USD/h
West US 3 (US) / westus3
4.9319 USD/h 26.688 USD/h
Central India (IN) / centralindia
5.0864 USD/h 27.524 USD/h
Jio India Central (IN) / jioindiacentral
- 27.524 USD/h
Jio India West (IN) / jioindiawest
- 27.524 USD/h
Mexico Central (ZA) / mexicocentral
5.3025 USD/h 28.6933 USD/h
Canada Central (CA) / canadacentral
5.4251 USD/h 29.3568 USD/h
Canada East (CA) / canadaeast
5.4251 USD/h 29.3568 USD/h
Central US (US) / centralus
5.573 USD/h 30.157 USD/h
North Europe (IE) / northeurope
5.9183 USD/h 32.0256 USD/h
South Central US (US) / southcentralus
5.9184 USD/h 32.026 USD/h
UK South (GB) / uksouth
6.2137 USD/h 33.624 USD/h
UK West (GB) / ukwest
6.2137 USD/h 33.624 USD/h
France Central (FR) / francecentral
6.2143 USD/h 33.627 USD/h
West US (US) / westus
6.4115 USD/h 34.694 USD/h
Indonesia Central (ID) / indonesiacentral
6.4362 USD/h 34.8278 USD/h
Malaysia West (MY) / malaysiawest
6.4362 USD/h 34.8278 USD/h
Israel Central (IL) / israelcentral
6.5101 USD/h 35.228 USD/h
UAE North (AE) / uaenorth
6.5101 USD/h 35.228 USD/h
Qatar Central (QA) / qatarcentral
6.5105 USD/h 35.23 USD/h
South Africa North (ZA) / southafricanorth
6.6088 USD/h 35.762 USD/h
Spain Central (ES) / spaincentral
6.7487 USD/h 36.5187 USD/h
Austria East (AT) / austriaeast
6.9012 USD/h 37.344 USD/h
Germany West Central (DE) / germanywestcentral
6.9012 USD/h 37.344 USD/h
Poland Central (PL) / polandcentral
6.9012 USD/h 37.344 USD/h
Sweden Central (SE) / swedencentral
6.9047 USD/h 37.363 USD/h
Italy North (IT) / italynorth
6.9047 USD/h 37.3632 USD/h
West Europe (NL) / westeurope
6.9047 USD/h 37.3632 USD/h
Norway East (NO) / norwayeast
7.0527 USD/h 38.164 USD/h
Australia Central 2 (AU) / australiacentral2
3.8698 USD/h 38.6976 USD/h
Australia Central (AU) / australiacentral
7.1513 USD/h 38.6976 USD/h
Australia East (AU) / australiaeast
7.1513 USD/h 38.6976 USD/h
Australia Southeast (AU) / australiasoutheast
7.1514 USD/h 38.698 USD/h
Japan East (JP) / japaneast
7.1514 USD/h 38.698 USD/h
Japan West (JP) / japanwest
7.1514 USD/h 38.698 USD/h
Korea Central (KR) / koreacentral
7.1514 USD/h 38.698 USD/h
Korea South (KR) / koreasouth
7.1514 USD/h 38.698 USD/h
Southeast Asia (SG) / southeastasia
7.1514 USD/h 38.698 USD/h
South India (IN) / southindia
7.4733 USD/h 40.44 USD/h
New Zealand North (NZ) / newzealandnorth
7.5089 USD/h 40.6325 USD/h
Switzerland North (CH) / switzerlandnorth
7.5952 USD/h 41.0995 USD/h
UAE Central (AE) / uaecentral
7.6938 USD/h 41.633 USD/h
South Africa West (ZA) / southafricawest
8.2857 USD/h 44.836 USD/h
East Asia (HK) / eastasia
8.9399 USD/h 48.3762 USD/h
Germany North (DE) / germanynorth
8.9715 USD/h 48.547 USD/h
Brazil South (BR) / brazilsouth
9.6174 USD/h 52.042 USD/h
Switzerland West (CH) / switzerlandwest
9.8738 USD/h 53.4296 USD/h
Brazil Southeast (US) / brazilsoutheast
11.0969 USD/h 60.048 USD/h

Processor

vCPUs
64
Hypervisor
Microsoft Hyper-V
CPU Allocation
Dedicated
CPU Cores
32
CPU Speed
2.7 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU Model
8280L
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
2 MiB
CPU L2 Cache Total
64 MiB
CPU L3 Cache
105 MiB
CPU L3 Cache Total
210 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, cpuid, pni, pclmulqdq, vmx, ssse3, fma, cx16, pcid, sse4_1, sse4_2, movbe, popcnt, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, abm, 3dnowprefetch, pti, tpr_shadow, ept, vpid, fsgsbase, bmi1, hle, avx2, smep, bmi2, erms, invpcid, rtm, avx512f, avx512dq, rdseed, adx, smap, clflushopt, avx512cd, avx512bw, avx512vl, xsaveopt, xsavec, xsaves, vnmi, md_clear
Ecpus
42.1
Scalability
65.78

System Resources and Accelerators

MEMORY
Memory Amount
4 TB
Memory Amount Actual
4 TB
ACCELERATORS
Accelerator Count
0
Accelerator Memory Min
0 MiB
Accelerator Memory Total
0 MiB
Accelerators
    STORAGE
    Storage Size
    4194 GB
    Storage Type
    ssd
    Storages
    • 4194 GB ssd (temp disk)
    NETWORK
    Inbound Traffic
    0 GB/month
    Outbound Traffic
    0 GB/month
    IPv4
    0

    CPU and System Topology

    Server Description

    A memory-intensive server combining massive RAM capacity and local SSD storage with strong uncached memory bandwidth for database workloads.

    Memory OptimizedStorage & Database

    Microsoft Azure M128-64ms is an x86_64 memory-optimized server configured with 64 dedicated vCPUs from 32 physical Intel Xeon 8280L cores at 2.7 GHz. It features a massive 3892.0 GB of RAM, providing 60.81 GB of memory per core, alongside 4194 GB of local SSD storage. Benchmark results reveal a significant performance tradeoff: while uncached memory read and write bandwidth are strong, single-core CPU performance is poor. Multi-core CPU execution, Passmark database operations, and Redis SET throughput perform in the average tier. This hardware profile is qualitatively cost-efficient for memory-bound applications requiring vast RAM capacity, such as large in-memory databases and heavy data processing, but is inefficient for compute-heavy or single-threaded tasks.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    1.9Score
    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) 4,643,611 ops/sec 1,919,289 ops/sec 2.4 50.00% 50.00% +55.00%
    Redis RPS (pipeline=16, SET) 27,337,770 ops/sec 11,728,058 ops/sec 2.2 20.00% 20.00% +17.00%
    PassMark Memory Mark (composite) 1,889 2,416 0.79 10.00% 10.00% -2.30%
    Memory bandwidth (read, 16 MB ~ L3) 314,577 MB/sec 108,466 MB/sec 2.8 10.00% 10.00% +11.00%
    PassMark single-thread CPU 1,492 Mops/s 2,365 Mops/s 0.62 10.00% 10.00% -4.70%

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 897

    Geekbench Multi-Core

    Score: 9,408

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    35,789
    Compression
    643,305
    Encryption
    20,170
    Extended Instructions
    47,222
    Floating Point Maths
    78,520
    Integer Maths
    146,382
    Physics
    4,978
    Prime Numbers
    288
    Single Threaded
    1,492
    String Sorting
    75,648

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    1,889
    Database Operations
    16,642
    Memory Latency
    73
    Memory Read Cached
    18,211
    Memory Read Uncached
    6,641
    Memory Write
    6,375

    Stress-ng Stressors

    CPU integerSingleMultiScaling
    atomic
    102.67 69.35 0.68×
    bitops
    95,552 3,666,127 38.37×
    branch
    88,881 4,415,386 49.68×
    funccall
    480.03 20,125 41.92×
    funcret
    7,963 403,549 50.68×
    hash
    113,897 5,279,547 46.35×
    intmath
    41,766 1,529,363 36.62×
    nop
    169,997 4,410,245 25.94×
    prime
    315,869 11,819,130 37.42×
    rotate
    63,954 2,179,320 34.08×
    str
    599,260 28,823,844 48.10×
    wcs
    422,369 17,425,234 41.26×
    CryptographySingleMultiScaling
    crypt
    2,176 64,733 29.75×
    CompressionSingleMultiScaling
    jpeg
    527.19 21,712 41.18×
    zlib
    42.01 2,012 47.89×
    HypervisorSingleMultiScaling
    clock
    16,757 142,884 8.53×
    clone
    1,158 22,260 19.22×
    context
    1,909 105,438 55.23×
    cpu-sched
    69.63 4,103 58.92×
    eventfd
    28,031 2,666,540 95.13×
    fault
    11,964 159,668 13.35×
    fork
    3,622 40,401 11.15×
    getrandom
    36,552 1,759,737 48.14×
    hrtimers
    425,150 5,784,979 13.61×
    mprotect
    501,771 10,354,721 20.64×
    mtx
    10,997,214 1,032,516,023 93.89×
    munmap
    2,745 41,320 15.05×
    null
    227,229 12,145,335 53.45×
    pipe
    505,747 23,426,481 46.32×
    priv-instr
    407,435 7,024,622 17.24×
    resched
    7,159,268 3,217,935 0.45×
    switch
    51,507 11,207,411 217.59×
    timermix
    157,267 7,789,495 49.53×
    tlb-shootdown
    3,641 64,537 17.73×
    tsc
    583,654 28,395,695 48.65×
    usersyscall
    299,232 7,096,192 23.71×
    vdso
    54,998,404 2,691,692,961 48.94×
    vfork
    18,082 127,169 7.03×
    x86syscall
    2,583,250 138,040,929 53.44×
    yield
    38,443,058 35,416,619 0.92×
    zero
    1,693,912 83,459,376 49.27×
    CPU float/SIMDSingleMultiScaling
    eigen
    10,410 420,881 40.43×
    expmath
    2,257 104,420 46.26×
    fma
    889,791 39,555,741 44.46×
    fp
    198.58 9,815 49.42×
    fractal
    4.6 206.52 44.90×
    hyperbolic
    2,600 120,399 46.30×
    logmath
    3,339 168,615 50.50×
    matrix
    3,896 140,144 35.97×
    matrix-3d
    507.95 6,558 12.91×
    monte-carlo
    107.49 6,042 56.21×
    mpfr
    1,121 39,440 35.17×
    powmath
    1,246 60,242 48.33×
    trig
    1,719 71,722 41.73×
    veccmp
    16,568 570,915 34.46×
    vecfp
    1,569 55,755 35.53×
    vecmath
    2,518 114,227 45.36×
    vecshuf
    2,466 148,058 60.03×
    vecwide
    53,956 2,154,179 39.93×
    AlgorithmsSingleMultiScaling
    bitonicsort
    5.6 217.99 38.93×
    bsearch
    185.34 7,686 41.47×
    bubblesort
    0.6 25.6 42.67×
    fibsearch
    199.39 7,968 39.96×
    heapsort
    6.4 274.39 42.87×
    hsearch
    5,287 207,649 39.28×
    insertionsort
    8.2 229.8 28.02×
    malloc
    1,686,080 44,910,922 26.64×
    mcontend
    52.15 7,476 143.35×
    mergesort
    19.6 905.97 46.22×
    qsort
    14.2 635.98 44.79×
    skiplist
    3,518 177,550 50.47×
    tree
    1.2 38.4 32.00×
    MemorySingleMultiScaling
    cache
    134,476 5,422,597 40.32×
    cachehammer
    207,508 6,340,964 30.56×
    cacheline
    25.16 1,949 77.46×
    l1cache
    697.33 8,619 12.36×
    memcpy
    283.96 8,782 30.93×
    memrate
    0.78 23.61 30.27×
    memthrash
    116.76 890.36 7.63×
    ptr-chase
    28,169,161 555,507,731 19.72×
    spinmem
    239.59 924.6 3.86×
    stream
    1.33 2,952 2219.50×
    vm
    59,720 301,362 5.05×

    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
    M8-2ms 2219 GiB0
    M8-4ms 4219 GiB0
    M16-4ms 4438 GiB0
    M8ms 8219 GiB0
    M16-8ms 8438 GiB0
    M32-8ms 8875 GiB0
    M16ms 16438 GiB0

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYAccelerators

    M128-64ms FAQs