D96pds_v6 by Microsoft Azure

D96pds_v6 is a Dpdsv6 family [ARM processor] [Local Disk] [Premium Storage capable] 96 vCPUs server offered by Microsoft Azure with 96 vCPUs, 384 GiB of memory and 5.67 TB of storage. The pricing starts at 0.5891 USD per hour.
96 vCPU
384 GiB Memory
5.67 TB Storage
Spare SCore
198,273
(All-cores)
2,075
(Single-core)

Specifications

Server Metadata

Vendor ID
azure
Server ID
Standard_D96pds_v6
Name
D96pds_v6
API Reference
Standard_D96pds_v6
Description
Dpdsv6 family [ARM processor] [Local Disk] [Premium Storage capable] 96 vCPUs
Family
Dpdsv6
Hw Virt
Average Time To Start
126
Status
active
Observed At
2026-11-03T09:14:20.026071

Availability

REGION / IDSPOTONDEMAND
Central India (IN) / centralindia
0.5891 USD/h 2.899 USD/h
East US 2 (US) / eastus2
0.8142 USD/h 4.406 USD/h
North Central US (US) / northcentralus
0.8142 USD/h 4.406 USD/h
West US 2 (US) / westus2
0.8142 USD/h 4.406 USD/h
West US 3 (US) / westus3
0.8142 USD/h 4.406 USD/h
East US (US) / eastus
1.9232 USD/h 4.406 USD/h
Sweden Central (SE) / swedencentral
0.9538 USD/h 4.694 USD/h
Mexico Central (ZA) / mexicocentral
0.8959 USD/h 4.848 USD/h
Canada Central (CA) / canadacentral
0.9048 USD/h 4.896 USD/h
Canada East (CA) / canadaeast
0.9048 USD/h 4.896 USD/h
Spain Central (ES) / spaincentral
0.9101 USD/h 4.925 USD/h
North Europe (IE) / northeurope
1.6154 USD/h 4.925 USD/h
Central US (US) / centralus
1.0612 USD/h 4.982 USD/h
UK South (GB) / uksouth
1.0324 USD/h 5.078 USD/h
Italy North (IT) / italynorth
0.9473 USD/h 5.126 USD/h
Indonesia Central (ID) / indonesiacentral
0.9526 USD/h 5.155 USD/h
West US (US) / westus
0.9526 USD/h 5.155 USD/h
France Central (FR) / francecentral
1.0001 USD/h 5.155 USD/h
Germany West Central (DE) / germanywestcentral
0.9739 USD/h 5.27 USD/h
Poland Central (PL) / polandcentral
0.9739 USD/h 5.27 USD/h
West Europe (NL) / westeurope
1.0709 USD/h 5.27 USD/h
South Central US (US) / southcentralus
0.9776 USD/h 5.29 USD/h
West Central US (US) / westcentralus
0.9776 USD/h 5.29 USD/h
UK West (GB) / ukwest
0.9865 USD/h 5.338 USD/h
UAE North (AE) / uaenorth
0.9935 USD/h 5.376 USD/h
Southeast Asia (SG) / southeastasia
1.0147 USD/h 5.491 USD/h
Australia East (AU) / australiaeast
1.1158 USD/h 5.491 USD/h
Japan East (JP) / japaneast
1.0467 USD/h 5.664 USD/h
Japan West (JP) / japanwest
1.0502 USD/h 5.683 USD/h
Austria East (AT) / austriaeast
1.0585 USD/h 5.728 USD/h
Belgium Central (BE) / belgiumcentral
1.0585 USD/h 5.728 USD/h
Denmark East (DK) / denmarkeast
1.0585 USD/h 5.728 USD/h
Australia Southeast (AU) / australiasoutheast
1.0591 USD/h 5.731 USD/h
Korea Central (KR) / koreacentral
1.0626 USD/h 5.75 USD/h
New Zealand North (NZ) / newzealandnorth
1.0663 USD/h 5.77 USD/h
East Asia (HK) / eastasia
1.1212 USD/h 6.067 USD/h
South Africa North (ZA) / southafricanorth
1.1424 USD/h 6.182 USD/h
Norway East (NO) / norwayeast
1.1655 USD/h 6.307 USD/h
South India (IN) / southindia
1.2297 USD/h 6.654 USD/h
Switzerland North (CH) / switzerlandnorth
1.2703 USD/h 6.874 USD/h
Brazil South (BR) / brazilsouth
1.2951 USD/h 7.008 USD/h
South Africa West (ZA) / southafricawest
1.4821 USD/h 8.02 USD/h
Switzerland West (CH) / switzerlandwest
1.5146 USD/h 8.196 USD/h
UAE Central (AE) / uaecentral
1.5146 USD/h 8.196 USD/h

Processor

vCPUs
96
Hypervisor
Microsoft Hyper-V
CPU Allocation
Dedicated
CPU Cores
96
CPU Speed
3.4 GHz
CPU Architecture
arm64
CPU Manufacturer
Microsoft
CPU Family
ARM
CPU Model
Neoverse-N2
CPU L1D Cache
64 KiB
CPU L1D Cache Total
6 MiB
CPU L1I Cache
64 KiB
CPU L1I Cache Total
6 MiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
96 MiB
CPU L3 Cache
128 MiB
CPU L3 Cache Total
128 MiB
CPU Flags
fp, asimd, evtstrm, aes, pmull, sha1, sha2, crc32, atomics, fphp, asimdhp, cpuid, asimdrdm, jscvt, fcma, lrcpc, dcpop, sha3, sm3, sm4, asimddp, sha512, sve, asimdfhm, uscat, ilrcpc, flagm, ssbs, sb, paca, pacg, dcpodp, sve2, sveaes, svebitperm, svesha3, svesm4, flagm2, frint, svei8mm, svebf16, i8mm, bf16
Ecpus
95.6
Scalability
99.58

System Resources and Accelerators

MEMORY
Memory Amount
384 GiB
Memory Amount Actual
384 GiB
ACCELERATORS
Accelerator Count
0
Accelerator Memory Min
0 MiB
Accelerator Memory Total
0 MiB
Accelerators
    STORAGE
    Storage Size
    5669 GB
    Storage Type
    nvme ssd
    Storages
    • 5669 GB nvme ssd
    NETWORK
    Inbound Traffic
    0 GB/month
    Outbound Traffic
    0 GB/month
    IPv4
    0

    CPU and System Topology

    Server Description

    A high-density ARM64 virtual machine featuring 96 dedicated cores and fast local NVMe storage for demanding multi-threaded workloads.

    General PurposeStorage & Database

    Microsoft Azure D96pds_v6 is a general-purpose virtual machine powered by a dedicated 96-core ARM64 Microsoft Neoverse-N2 processor running at 3.4 GHz. It features 384.0 GB of RAM and a 5669 GB local NVMe SSD, operating on the Microsoft Hyper-V hypervisor. The instance delivers top-tier multi-core CPU performance, exceptional memory bandwidth, and high-speed database operations, as demonstrated by top-tier results in multi-threaded benchmarks, Redis SET operations, and static web serving throughput. Single-core performance remains in the average range. Given its balanced resource allocation and high-capacity local storage, the D96pds_v6 is highly cost-efficient for multi-threaded workloads. It is recommended for database hosting, high-throughput web serving, software compilation, and data-intensive applications.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    5.4Score
    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) 16,692,666 ops/sec 1,920,103 ops/sec 8.9 50.00% 50.00% +200.00%
    Redis RPS (pipeline=16, SET) 104,232,553 ops/sec 11,744,104 ops/sec 8.3 20.00% 20.00% +53.00%
    PassMark Memory Mark (composite) 3,409 2,415 1.4 10.00% 10.00% +3.40%
    Memory bandwidth (read, 16 MB ~ L3) 510,052 MB/sec 108,490 MB/sec 4.6 10.00% 10.00% +16.00%
    PassMark single-thread CPU 1,878 Mops/s 2,365 Mops/s 0.79 10.00% 10.00% -2.30%

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 1,704

    Geekbench Multi-Core

    Score: 23,821

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 56,533
    Compression
    		 657,237
    Encryption
    		 18,048
    Extended Instructions
    		 85,611
    Floating Point Maths
    		 507,175
    Integer Maths
    		 603,704
    Physics
    		 18,513
    Prime Numbers
    		 631
    Single Threaded
    		 1,878
    String Sorting
    		 477,592

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 3,409
    Database Operations
    		 38,194
    Memory Latency
    		 52
    Memory Read Cached
    		 25,385
    Memory Read Uncached
    		 19,748
    Memory Write
    		 25,740

    Stress-ng Stressors

    CPU integerSingleMultiScaling
    atomic
    		 158.04 9.17 0.06×
    bitops
    		 151,318 14,458,196 95.55×
    branch
    		 256,643 24,538,070 95.61×
    funccall
    		 1,906 182,278 95.62×
    funcret
    		 33,414 3,129,689 93.66×
    hash
    		 177,666 16,999,769 95.68×
    intmath
    		 39,127 3,739,377 95.57×
    nop
    		 456,893 43,716,375 95.68×
    prime
    		 487,937 46,631,392 95.57×
    rotate
    		 130,677 12,505,901 95.70×
    str
    		 695,194 65,678,815 94.48×
    wcs
    		 217,560 20,794,045 95.58×
    CryptographySingleMultiScaling
    crypt
    		 3,812 364,893 95.72×
    CompressionSingleMultiScaling
    jpeg
    		 690.75 65,637 95.02×
    zlib
    		 56.62 4,432 78.27×
    HypervisorSingleMultiScaling
    clock
    		 26,632 260,061 9.77×
    clone
    		 306.77 9,318 30.38×
    context
    		 2,735 262,973 96.16×
    cpu-sched
    		 61.42 6,198 100.92×
    eventfd
    		 52,037 2,293,639 44.08×
    fault
    		 22,471 387,354 17.24×
    fork
    		 3,685 70,571 19.15×
    getrandom
    		 60,019 5,742,080 95.67×
    hrtimers
    		 682,986 10,419,647 15.26×
    mprotect
    		 1,051,146 20,014,757 19.04×
    mtx
    		 9,313,014 4,466,215,754 479.57×
    munmap
    		 2,714 80,171 29.54×
    null
    		 482,188 46,368,133 96.16×
    pipe
    		 904,384 43,412,805 48.00×
    priv-instr
    		 847,168 10,683,577 12.61×
    resched
    		 2,077,895 10,271,766 4.94×
    switch
    		 80,166 48,361,683 603.27×
    timermix
    		 626,934 59,298,897 94.59×
    tlb-shootdown
    		 15,484 233,345 15.07×
    vdso
    		 46,179,357 4,457,250,311 96.52×
    vfork
    		 26,586 264,630 9.95×
    yield
    		 115,180,594 129,507,146 1.12×
    zero
    		 2,757,011 264,362,891 95.89×
    CPU float/SIMDSingleMultiScaling
    eigen
    		 2,129 203,472 95.59×
    expmath
    		 393.39 37,602 95.58×
    fma
    		 768,373 73,455,388 95.60×
    fp
    		 162.94 15,400 94.52×
    fractal
    		 7.8 737.99 94.61×
    hyperbolic
    		 387.28 37,061 95.69×
    logmath
    		 465.37 44,535 95.70×
    matrix
    		 6,609 632,247 95.66×
    matrix-3d
    		 1,074 21,507 20.02×
    monte-carlo
    		 214.4 19,853 92.60×
    mpfr
    		 1,448 138,297 95.53×
    powmath
    		 272.11 26,042 95.70×
    trig
    		 520.86 49,824 95.66×
    veccmp
    		 19,402 1,857,094 95.71×
    vecfp
    		 914.03 87,461 95.69×
    vecmath
    		 4,873 466,264 95.69×
    vecshuf
    		 1,008 96,441 95.71×
    vecwide
    		 27,469 2,602,927 94.76×
    AlgorithmsSingleMultiScaling
    bitonicsort
    		 9.4 892.78 94.98×
    bsearch
    		 382.06 36,473 95.46×
    bubblesort
    		 1.2 115.2 96.00×
    fibsearch
    		 432.35 41,371 95.69×
    heapsort
    		 13.2 1,266 95.89×
    hsearch
    		 6,975 669,824 96.03×
    insertionsort
    		 7.6 730 96.05×
    malloc
    		 2,905,631 170,433,051 58.66×
    mcontend
    		 230.06 230,513 1001.97×
    mergesort
    		 37.8 3,583 94.80×
    qsort
    		 24.4 2,341 95.94×
    skiplist
    		 7,027 671,963 95.63×
    tree
    		 1.4 71.09 50.78×
    MemorySingleMultiScaling
    cache
    		 441,230 5,245,195 11.89×
    cachehammer
    		 1,659,971 22,427,669 13.51×
    cacheline
    		 80.36 5,595 69.62×
    l1cache
    		 302.63 27,929 92.29×
    memcpy
    		 723.61 69,249 95.70×
    memrate
    		 5.34 71.13 13.32×
    memthrash
    		 277.96 690.37 2.48×
    ptr-chase
    		 22,679,413 746,613,284 32.92×
    spinmem
    		 3,565 97,865 27.45×
    stream
    		 12.21 15,104 1237.05×
    vm
    		 139,269 6,961,741 49.99×

    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
    D2pds_v6 28 GiB0
    D4pds_v6 416 GiB0
    D8pds_v6 832 GiB0
    D16pds_v6 1664 GiB0
    D32pds_v6 32128 GiB0
    D48pds_v6 48192 GiB0
    D64pds_v6 64256 GiB0

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYAccelerators

    D96pds_v6 FAQs