FX32mds_v2 by Microsoft Azure

FX32mds_v2 is a FXmdsv2 family [Memory Intensive] [Local Disk] [Premium Storage capable] [Intel processor] 32 vCPUs server offered by Microsoft Azure with 32 vCPUs, 672 GiB of memory and 1.89 TB of storage. The pricing starts at 0.8089 USD per hour.
32 vCPU
672 GiB Memory
1.89 TB Storage
Spare SCore
35,521
(All-cores)
2,167
(Single-core)

Specifications

Server Metadata

Vendor ID
azure
Server ID
Standard_FX32mds_v2
Name
FX32mds_v2
API Reference
Standard_FX32mds_v2
Description
FXmdsv2 family [Memory Intensive] [Local Disk] [Premium Storage capable] [Intel processor] 32 vCPUs
Family
FXmdsv2
Hw Virt
Average Time To Start
81
Status
active
Observed At
2026-10-25T04:45:15.494126

Availability

REGION / IDSPOTONDEMAND
East US 2 (US) / eastus2
0.8089 USD/h 4.377 USD/h
West US 3 (US) / westus3
0.8089 USD/h 4.377 USD/h
East US (US) / eastus
0.9187 USD/h 4.377 USD/h
West US 2 (US) / westus2
0.8091 USD/h 4.378 USD/h
Central India (IN) / centralindia
0.8347 USD/h 4.517 USD/h
Canada Central (CA) / canadacentral
0.89 USD/h 4.816 USD/h
Central US (US) / centralus
0.913 USD/h 4.946 USD/h
Sweden Central (SE) / swedencentral
0.9225 USD/h 4.992 USD/h
Indonesia Central (ID) / indonesiacentral
0.9464 USD/h 5.121 USD/h
South Central US (US) / southcentralus
0.9706 USD/h 5.252 USD/h
West Central US (US) / westcentralus
0.9706 USD/h 5.252 USD/h
North Europe (IE) / northeurope
0.9708 USD/h 5.253 USD/h
Spain Central (ES) / spaincentral
0.9708 USD/h 5.253 USD/h
UK West (GB) / ukwest
0.9787 USD/h 5.296 USD/h
Qatar Central (QA) / qatarcentral
0.9951 USD/h 5.385 USD/h
UAE North (AE) / uaenorth
0.9951 USD/h 5.385 USD/h
France Central (FR) / francecentral
1.0194 USD/h 5.516 USD/h
UK South (GB) / uksouth
1.0194 USD/h 5.516 USD/h
Australia Southeast (AU) / australiasoutheast
1.0515 USD/h 5.69 USD/h
Austria East (AT) / austriaeast
1.0515 USD/h 5.69 USD/h
Belgium Central (BE) / belgiumcentral
1.0515 USD/h 5.69 USD/h
West US (US) / westus
1.0517 USD/h 5.691 USD/h
Chile Central (CL) / chilecentral
1.1323 USD/h 6.127 USD/h
Germany West Central (DE) / germanywestcentral
1.1326 USD/h 6.129 USD/h
West Europe (NL) / westeurope
1.1326 USD/h 6.129 USD/h
South India (IN) / southindia
1.1404 USD/h 6.171 USD/h
South Africa North (ZA) / southafricanorth
1.1554 USD/h 6.252 USD/h
Southeast Asia (SG) / southeastasia
1.1727 USD/h 6.346 USD/h
Australia East (AU) / australiaeast
1.1731 USD/h 6.348 USD/h
Japan East (JP) / japaneast
1.1731 USD/h 6.348 USD/h
Korea Central (KR) / koreacentral
1.1731 USD/h 6.348 USD/h
New Zealand North (NZ) / newzealandnorth
1.2313 USD/h 6.663 USD/h
Switzerland North (CH) / switzerlandnorth
1.2459 USD/h 6.742 USD/h
Germany North (DE) / germanynorth
1.4725 USD/h 7.968 USD/h
Brazil South (BR) / brazilsouth
1.5776 USD/h 8.537 USD/h

Processor

vCPUs
32
Hypervisor
Microsoft Hyper-V
CPU Allocation
Dedicated
CPU Cores
16
CPU Speed
4.2 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU Model
8573C
CPU L1D Cache
48 KiB
CPU L1D Cache Total
768 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
512 KiB
CPU L2 Cache
2 MiB
CPU L2 Cache Total
32 MiB
CPU L3 Cache
260 MiB
CPU L3 Cache Total
520 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, tsc_reliable, nonstop_tsc, cpuid, aperfmperf, tsc_known_freq, pni, pclmulqdq, vmx, ssse3, fma, cx16, pcid, sse4_1, sse4_2, x2apic, movbe, popcnt, tsc_deadline_timer, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, abm, 3dnowprefetch, tpr_shadow, ept, vpid, ept_ad, 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, user_shstk, avx_vnni, avx512_bf16, vnmi, avx512vbmi, umip, waitpkg, avx512_vbmi2, gfni, vaes, vpclmulqdq, avx512_vnni, avx512_bitalg, avx512_vpopcntdq, la57, rdpid, cldemote, movdiri, movdir64b, fsrm, serialize, tsxldtrk, ibt, amx_bf16, avx512_fp16, amx_tile, amx_int8, arch_capabilities
Ecpus
16.4
Scalability
51.25

System Resources and Accelerators

MEMORY
Memory Amount
672 GiB
Memory Amount Actual
672 GiB
ACCELERATORS
Accelerator Count
0
Accelerator Memory Min
0 MiB
Accelerator Memory Total
0 MiB
Accelerators
    STORAGE
    Storage Size
    1890 GB
    Storage Type
    nvme ssd
    Storages
    • 1890 GB nvme ssd
    NETWORK
    Inbound Traffic
    0 GB/month
    Outbound Traffic
    0 GB/month
    IPv4
    0

    CPU and System Topology

    Server Description

    A memory-intensive virtual machine featuring high-frequency Intel Xeon processing, substantial RAM capacity, and fast local NVMe SSD storage.

    Memory OptimizedStorage & Database

    Microsoft Azure FX32mds_v2 is a memory-optimized virtual machine featuring 32 dedicated vCPUs and 16 physical cores powered by an Intel Xeon 8573C processor running at 4.2 GHz. Built on the x86_64 architecture, it includes 672.0 GB of RAM and a bundled 1890 GB local NVMe SSD. Benchmark results highlight top-tier single-core and text processing performance, alongside strong large-block memory bandwidth of 232.79 GB/sec read and 136.78 GB/sec write. While its CPU-based LLM inference for small models is strong, large-model text generation is a bottleneck due to the lack of dedicated GPU hardware. This instance is designed for memory-intensive workloads, including large-scale database operations, in-memory caching, and data-intensive enterprise applications requiring high-frequency processing and substantial memory capacity.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    2.8Score
    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) 6,732,606 ops/sec 1,919,289 ops/sec 3.5 50.00% 50.00% +87.00%
    Redis RPS (pipeline=16, SET) 34,071,172 ops/sec 11,728,058 ops/sec 2.8 20.00% 20.00% +23.00%
    PassMark Memory Mark (composite) 2,711 2,416 1.1 10.00% 10.00% +0.96%
    Memory bandwidth (read, 16 MB ~ L3) 488,491 MB/sec 108,466 MB/sec 4.5 10.00% 10.00% +16.00%
    PassMark single-thread CPU 3,246 Mops/s 2,365 Mops/s 1.3 10.00% 10.00% +2.70%

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 2,313

    Geekbench Multi-Core

    Score: 18,003

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 52,531
    Compression
    		 621,815
    Encryption
    		 37,336
    Extended Instructions
    		 50,417
    Floating Point Maths
    		 120,579
    Integer Maths
    		 170,166
    Physics
    		 7,846
    Prime Numbers
    		 339
    Single Threaded
    		 3,246
    String Sorting
    		 84,637

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 2,711
    Database Operations
    		 20,148
    Memory Latency
    		 58
    Memory Read Cached
    		 28,876
    Memory Read Uncached
    		 10,802
    Memory Write
    		 10,007

    Stress-ng Stressors

    CPU integerSingleMultiScaling
    atomic
    		 212.99 203.77 0.96×
    bitops
    		 166,599 3,209,816 19.27×
    branch
    		 156,551 3,866,876 24.70×
    funccall
    		 843.02 17,794 21.11×
    funcret
    		 14,131 351,138 24.85×
    hash
    		 198,065 4,525,836 22.85×
    intmath
    		 73,343 1,391,710 18.98×
    nop
    		 296,600 3,782,468 12.75×
    prime
    		 529,311 10,173,459 19.22×
    rotate
    		 111,414 1,891,277 16.98×
    str
    		 1,006,095 24,230,437 24.08×
    wcs
    		 741,714 15,139,052 20.41×
    CryptographySingleMultiScaling
    crypt
    		 3,794 68,807 18.14×
    CompressionSingleMultiScaling
    jpeg
    		 920.07 19,268 20.94×
    zlib
    		 64.7 1,697 26.23×
    HypervisorSingleMultiScaling
    clock
    		 38,672 184,065 4.76×
    clone
    		 1,164 17,443 14.99×
    context
    		 5,944 156,841 26.39×
    cpu-sched
    		 75.81 2,032 26.80×
    eventfd
    		 43,437 1,263,718 29.09×
    fault
    		 24,191 179,266 7.41×
    fork
    		 6,513 47,931 7.36×
    getrandom
    		 65,670 1,559,400 23.75×
    hrtimers
    		 328,421 5,049,622 15.38×
    mprotect
    		 582,970 10,279,143 17.63×
    mtx
    		 25,491,005 1,039,299,849 40.77×
    munmap
    		 5,024 43,452 8.65×
    null
    		 978,227 24,348,268 24.89×
    pipe
    		 738,248 20,719,346 28.07×
    priv-instr
    		 966,393 13,355,400 13.82×
    resched
    		 10,017,504 2,489,725 0.25×
    switch
    		 44,875 11,500,109 256.27×
    timermix
    		 271,107 6,554,187 24.18×
    tlb-shootdown
    		 6,838 55,392 8.10×
    tsc
    		 1,019,992 24,725,091 24.24×
    usersyscall
    		 814,186 12,680,003 15.57×
    vdso
    		 119,294,170 2,795,215,643 23.43×
    vfork
    		 28,346 170,083 6.00×
    x86syscall
    		 11,722,938 316,586,084 27.01×
    yield
    		 51,298,074 40,452,868 0.79×
    zero
    		 6,512,636 172,601,665 26.50×
    CPU float/SIMDSingleMultiScaling
    eigen
    		 18,119 351,791 19.42×
    expmath
    		 3,946 91,484 23.19×
    fma
    		 1,461,170 30,277,950 20.72×
    fp
    		 229.07 5,478 23.91×
    fractal
    		 7.2 167.54 23.27×
    hyperbolic
    		 4,554 104,841 23.02×
    logmath
    		 5,820 147,309 25.31×
    matrix
    		 5,743 110,036 19.16×
    matrix-3d
    		 767.13 11,359 14.81×
    monte-carlo
    		 334.08 8,686 26.00×
    mpfr
    		 1,965 36,279 18.46×
    powmath
    		 2,198 53,427 24.31×
    trig
    		 2,999 63,008 21.01×
    veccmp
    		 28,030 519,148 18.52×
    vecfp
    		 1,731 35,431 20.47×
    vecmath
    		 4,390 98,520 22.44×
    vecshuf
    		 924.66 16,940 18.32×
    vecwide
    		 40,144 786,903 19.60×
    AlgorithmsSingleMultiScaling
    bitonicsort
    		 10 190.4 19.04×
    bsearch
    		 322.57 6,676 20.70×
    bubblesort
    		 1.2 25 20.83×
    fibsearch
    		 343.16 6,587 19.20×
    heapsort
    		 11.2 245.39 21.91×
    hsearch
    		 9,441 185,706 19.67×
    insertionsort
    		 14.4 207 14.38×
    malloc
    		 3,131,569 38,389,620 12.26×
    mcontend
    		 58.7 5,675 96.68×
    mergesort
    		 34.2 785.38 22.96×
    qsort
    		 24.6 549.19 22.32×
    skiplist
    		 6,108 155,248 25.42×
    tree
    		 1.8 44.8 24.89×
    MemorySingleMultiScaling
    cache
    		 276,883 3,423,135 12.36×
    cachehammer
    		 206,729 3,638,668 17.60×
    cacheline
    		 44.76 2,629 58.74×
    l1cache
    		 1,218 7,432 6.10×
    memcpy
    		 497.95 7,782 15.63×
    memrate
    		 0.13 3.95 30.38×
    memthrash
    		 91.4 838.47 9.17×
    ptr-chase
    		 36,410,134 794,706,080 21.83×
    spinmem
    		 314.38 1,654 5.26×
    stream
    		 3.32 1,684 507.13×
    vm
    		 205,527 297,312 1.45×

    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
    FX2mds_v2 242 GiB0
    FX4-2mds_v2 284 GiB0
    FX8-2mds_v2 2168 GiB0
    FX4mds_v2 484 GiB0
    FX8-4mds_v2 4168 GiB0
    FX16-4mds_v2 4336 GiB0
    FX12-6mds_v2 6252 GiB0

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYAccelerators

    FX32mds_v2 FAQs