B12ms by Microsoft Azure

B12ms is a BS family [Memory Intensive] [Premium Storage capable] [Intel processor] 12 vCPUs server offered by Microsoft Azure with 12 vCPUs, 48 GiB of memory and 98 GB of storage. The pricing starts at 0.499 USD per hour.
12 vCPU
48 GiB Memory
98 GB Storage
Spare SCore
12,139
(All-cores)
1,040
(Single-core)

Specifications

Server Metadata

Vendor ID
azure
Server ID
Standard_B12ms
Name
B12ms
API Reference
Standard_B12ms
Description
BS family [Memory Intensive] [Premium Storage capable] [Intel processor] 12 vCPUs
Family
BS
Hw Virt
Average Time To Start
26
Status
planned-for-retirement
Observed At
2026-10-28T20:04:35.528276

Availability

REGION / IDSPOTONDEMAND
East US (US) / eastus
- 0.499 USD/h
East US 2 (US) / eastus2
- 0.499 USD/h
North Central US (US) / northcentralus
- 0.499 USD/h
West US 2 (US) / westus2
- 0.499 USD/h
West US 3 (US) / westus3
- 0.499 USD/h
Sweden Central (SE) / swedencentral
- 0.518 USD/h
Central India (IN) / centralindia
- 0.538 USD/h
Jio India Central (IN) / jioindiacentral
- 0.538 USD/h
Jio India West (IN) / jioindiawest
- 0.538 USD/h
North Europe (IE) / northeurope
- 0.546 USD/h
Mexico Central (ZA) / mexicocentral
- 0.549 USD/h
Spain Central (ES) / spaincentral
- 0.549 USD/h
Canada Central (CA) / canadacentral
- 0.556 USD/h
Canada East (CA) / canadaeast
- 0.557 USD/h
UK West (GB) / ukwest
- 0.564 USD/h
France Central (FR) / francecentral
- 0.566 USD/h
UK South (GB) / uksouth
- 0.566 USD/h
Indonesia Central (ID) / indonesiacentral
- 0.57 USD/h
Malaysia West (MY) / malaysiawest
- 0.57 USD/h
Austria East (AT) / austriaeast
- 0.576 USD/h
Belgium Central (BE) / belgiumcentral
- 0.576 USD/h
Germany West Central (DE) / germanywestcentral
- 0.576 USD/h
Israel Central (IL) / israelcentral
- 0.576 USD/h
Italy North (IT) / italynorth
- 0.576 USD/h
Poland Central (PL) / polandcentral
- 0.576 USD/h
West Europe (NL) / westeurope
- 0.576 USD/h
West US (US) / westus
- 0.595 USD/h
Central US (US) / centralus
- 0.599 USD/h
South Central US (US) / southcentralus
- 0.599 USD/h
UAE North (AE) / uaenorth
- 0.599 USD/h
West Central US (US) / westcentralus
- 0.599 USD/h
Qatar Central (QA) / qatarcentral
- 0.602 USD/h
Korea South (KR) / koreasouth
- 0.622 USD/h
Korea Central (KR) / koreacentral
- 0.624 USD/h
Switzerland North (CH) / switzerlandnorth
- 0.6336 USD/h
Australia Central (AU) / australiacentral
- 0.634 USD/h
Australia Central 2 (AU) / australiacentral2
- 0.634 USD/h
Australia East (AU) / australiaeast
- 0.634 USD/h
Australia Southeast (AU) / australiasoutheast
- 0.634 USD/h
Norway East (NO) / norwayeast
- 0.634 USD/h
Southeast Asia (SG) / southeastasia
- 0.634 USD/h
South Africa North (ZA) / southafricanorth
- 0.651 USD/h
Japan East (JP) / japaneast
- 0.653 USD/h
New Zealand North (NZ) / newzealandnorth
- 0.665 USD/h
Chile Central (CL) / chilecentral
- 0.699 USD/h
East Asia (HK) / eastasia
- 0.701 USD/h
South India (IN) / southindia
- 0.706 USD/h
West India (IN) / westindia
- 0.714 USD/h
Japan West (JP) / japanwest
- 0.719 USD/h
Germany North (DE) / germanynorth
- 0.749 USD/h
UAE Central (AE) / uaecentral
- 0.749 USD/h
Brazil South (BR) / brazilsouth
- 0.806 USD/h
France South (FR) / francesouth
- 0.811 USD/h
South Africa West (ZA) / southafricawest
- 0.8137 USD/h
Switzerland West (CH) / switzerlandwest
- 0.8231 USD/h
Norway West (NO) / norwaywest
- 0.824 USD/h
Brazil Southeast (US) / brazilsoutheast
- 1.048 USD/h

Processor

vCPUs
12
Hypervisor
Microsoft Hyper-V
CPU Allocation
Burstable
CPU Cores
12
CPU Speed
2.6 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU Model
8272CL
CPU L1D Cache
32 KiB
CPU L1D Cache Total
384 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
384 KiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
12 MiB
CPU L3 Cache
36 MiB
CPU L3 Cache Total
36 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, ssse3, fma, cx16, pcid, sse4_1, sse4_2, movbe, popcnt, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, abm, 3dnowprefetch, pti, fsgsbase, bmi1, hle, avx2, smep, bmi2, erms, invpcid, rtm, avx512f, avx512dq, rdseed, adx, smap, clflushopt, avx512cd, avx512bw, avx512vl, xsaveopt, xsavec, xsaves, md_clear
Ecpus
11.7
Scalability
97.5

System Resources and Accelerators

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

    CPU and System Topology

    Server Description

    A burstable x86_64 virtual machine combining twelve Intel Xeon cores with forty-eight gigabytes of memory for variable multi-threaded workloads.

    Burstable & BudgetGeneral Purpose

    Microsoft Azure B12ms is an x86_64 burstable virtual machine from the BS server family, powered by an Intel Xeon 8272CL processor running at 2.6 GHz. It features 12 vCPUs, 12 physical cores, 48.0 GB of RAM, and 98 GB of local storage with Premium Storage capability. Benchmark results indicate a clear performance tradeoff: single-core CPU execution and single-threaded compression tasks are weak, placing in the bottom 25%, while multi-core operations, memory bandwidth, and database operations perform at an average level within the middle 50%. The burstable CPU allocation provides a cost-efficient resource model for variable workloads rather than sustained high-compute tasks. This configuration is suitable for database operations, Redis caching, and static web serving where resource demands fluctuate.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    0.84Score
    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) 1,556,314 ops/sec 1,919,289 ops/sec 0.84 50.00% 50.00% -8.30%
    Redis RPS (pipeline=16, SET) 9,684,434 ops/sec 11,728,058 ops/sec 0.81 20.00% 20.00% -4.10%
    PassMark Memory Mark (composite) 2,635 2,416 1.1 10.00% 10.00% +0.96%
    Memory bandwidth (read, 16 MB ~ L3) 87,173 MB/sec 108,466 MB/sec 0.79 10.00% 10.00% -2.30%
    PassMark single-thread CPU 1,843 Mops/s 2,365 Mops/s 0.75 10.00% 10.00% -2.80%

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 1,045

    Geekbench Multi-Core

    Score: 7,375

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 15,897
    Compression
    		 218,851
    Encryption
    		 5,556
    Extended Instructions
    		 18,369
    Floating Point Maths
    		 36,126
    Integer Maths
    		 43,175
    Physics
    		 1,735
    Prime Numbers
    		 118
    Single Threaded
    		 1,843
    String Sorting
    		 26,164

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 2,635
    Database Operations
    		 7,923
    Memory Latency
    		 49
    Memory Read Cached
    		 21,729
    Memory Read Uncached
    		 11,408
    Memory Write
    		 10,227

    Stress-ng Stressors

    CPU integerSingleMultiScaling
    atomic
    		 164.93 152.01 0.92×
    bitops
    		 83,290 961,263 11.54×
    branch
    		 114,733 1,329,242 11.59×
    funccall
    		 399.99 4,630 11.58×
    funcret
    		 8,320 96,119 11.55×
    hash
    		 92,443 1,069,646 11.57×
    intmath
    		 16,374 191,793 11.71×
    nop
    		 140,622 1,612,804 11.47×
    prime
    		 236,798 2,748,808 11.61×
    rotate
    		 70,034 822,763 11.75×
    str
    		 556,677 6,456,403 11.60×
    wcs
    		 349,364 4,024,281 11.52×
    CryptographySingleMultiScaling
    crypt
    		 1,799 20,855 11.59×
    CompressionSingleMultiScaling
    jpeg
    		 426.8 4,760 11.15×
    zlib
    		 32.99 419.58 12.72×
    HypervisorSingleMultiScaling
    clock
    		 16,693 141,974 8.51×
    clone
    		 906.53 6,899 7.61×
    context
    		 1,482 17,272 11.66×
    cpu-sched
    		 59.61 781.15 13.10×
    eventfd
    		 25,862 497,042 19.22×
    fault
    		 7,948 67,374 8.48×
    fork
    		 2,831 21,443 7.58×
    getrandom
    		 32,689 380,556 11.64×
    hrtimers
    		 122,060 1,518,121 12.44×
    mprotect
    		 870,514 2,117,175 2.43×
    mtx
    		 8,441,170 359,063,797 42.54×
    munmap
    		 1,890 19,174 10.14×
    null
    		 157,618 1,814,068 11.51×
    pipe
    		 768,637 3,566,135 4.64×
    priv-instr
    		 337,598 3,751,564 11.11×
    resched
    		 2,396,019 1,110,336 0.46×
    switch
    		 44,681 2,247,711 50.31×
    timermix
    		 154,621 1,797,227 11.62×
    tlb-shootdown
    		 6,813 25,954 3.81×
    tsc
    		 729,516 8,443,756 11.57×
    usersyscall
    		 235,489 2,658,610 11.29×
    vdso
    		 54,773,538 634,626,924 11.59×
    vfork
    		 15,884 133,707 8.42×
    x86syscall
    		 1,751,984 20,653,241 11.79×
    yield
    		 6,081,160 6,211,922 1.02×
    zero
    		 1,166,417 13,530,074 11.60×
    CPU float/SIMDSingleMultiScaling
    eigen
    		 12,118 137,840 11.38×
    expmath
    		 1,997 23,075 11.55×
    fma
    		 507,175 5,308,099 10.47×
    fp
    		 120 1,388 11.57×
    fractal
    		 3.8 43.6 11.47×
    hyperbolic
    		 2,071 24,052 11.62×
    logmath
    		 3,346 38,822 11.60×
    matrix
    		 2,382 27,545 11.57×
    matrix-3d
    		 538.02 3,218 5.98×
    monte-carlo
    		 84.95 969.61 11.41×
    mpfr
    		 888.36 10,317 11.61×
    powmath
    		 1,170 13,585 11.61×
    trig
    		 1,270 14,792 11.65×
    veccmp
    		 11,500 132,908 11.56×
    vecfp
    		 1,685 19,228 11.41×
    vecmath
    		 1,580 18,332 11.61×
    vecshuf
    		 679.64 8,085 11.90×
    vecwide
    		 41,922 488,398 11.65×
    AlgorithmsSingleMultiScaling
    bitonicsort
    		 5.4 61.19 11.33×
    bsearch
    		 178.57 2,087 11.69×
    bubblesort
    		 0.6 5.2 8.67×
    fibsearch
    		 178.92 2,074 11.59×
    heapsort
    		 6.2 70.2 11.32×
    hsearch
    		 3,561 42,076 11.82×
    insertionsort
    		 6 69.2 11.53×
    malloc
    		 1,608,090 16,675,202 10.37×
    mcontend
    		 97.84 2,511 25.66×
    mergesort
    		 17.4 199.19 11.45×
    qsort
    		 11 127.6 11.60×
    skiplist
    		 3,628 41,863 11.54×
    tree
    		 1.2 9.4 7.83×
    MemorySingleMultiScaling
    cache
    		 232,797 400,871 1.72×
    cachehammer
    		 358,134 3,975,397 11.10×
    cacheline
    		 21.53 257.25 11.95×
    l1cache
    		 167.17 1,907 11.41×
    memcpy
    		 256.65 2,960 11.53×
    memrate
    		 1.17 9.32 7.97×
    memthrash
    		 95.3 471.97 4.95×
    ptr-chase
    		 18,114,899 121,211,262 6.69×
    spinmem
    		 304.58 571.9 1.88×
    stream
    		 25.1 3,006 119.76×
    vm
    		 54,792 292,887 5.35×

    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

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYAccelerators

    B12ms FAQs