D4s_v3 by Microsoft Azure

D4s_v3 is a DSv3 family [Premium Storage capable] [Intel processor] 4 vCPUs server offered by Microsoft Azure with 4 vCPUs, 16 GiB of memory and 34 GB of storage. The pricing starts at 0.025 USD per hour.
4 vCPU
16 GiB Memory
34 GB Storage
Spare SCore
2,753
(All-cores)
1,073
(Single-core)

Specifications

Server Metadata

Vendor ID
azure
Server ID
Standard_D4s_v3
Name
D4s_v3
API Reference
Standard_D4s_v3
Description
DSv3 family [Premium Storage capable] [Intel processor] 4 vCPUs
Family
DSv3
Hw Virt
Average Time To Start
20
Status
planned-for-retirement
Observed At
2026-11-10T08:23:40.629553

Availability

REGION / IDSPOTONDEMAND
West US 2 (US) / westus2
0.0355 USD/h 0.192 USD/h
West US 3 (US) / westus3
0.0355 USD/h 0.192 USD/h
East US (US) / eastus
0.0384 USD/h 0.192 USD/h
East US 2 (US) / eastus2
0.0662 USD/h 0.192 USD/h
North Central US (US) / northcentralus
0.037 USD/h 0.2 USD/h
Sweden Central (SE) / swedencentral
0.0377 USD/h 0.204 USD/h
Central India (IN) / centralindia
0.0388 USD/h 0.21 USD/h
Jio India Central (IN) / jioindiacentral
- 0.21 USD/h
Jio India West (IN) / jioindiawest
- 0.21 USD/h
Mexico Central (ZA) / mexicocentral
0.039 USD/h 0.211 USD/h
North Europe (IE) / northeurope
0.0395 USD/h 0.214 USD/h
Spain Central (ES) / spaincentral
0.0395 USD/h 0.214 USD/h
Central US (US) / centralus
0.037 USD/h 0.22 USD/h
South Central US (US) / southcentralus
0.0407 USD/h 0.22 USD/h
West Central US (US) / westcentralus
0.0407 USD/h 0.22 USD/h
Korea South (KR) / koreasouth
0.0408 USD/h 0.221 USD/h
Canada East (CA) / canadaeast
0.041 USD/h 0.222 USD/h
Canada Central (CA) / canadacentral
0.0636 USD/h 0.222 USD/h
France Central (FR) / francecentral
0.0414 USD/h 0.224 USD/h
Israel Central (IL) / israelcentral
0.0414 USD/h 0.224 USD/h
Italy North (IT) / italynorth
0.0414 USD/h 0.224 USD/h
Indonesia Central (ID) / indonesiacentral
0.0416 USD/h 0.225 USD/h
Malaysia West (MY) / malaysiawest
0.0416 USD/h 0.225 USD/h
Germany West Central (DE) / germanywestcentral
0.0425 USD/h 0.23 USD/h
Poland Central (PL) / polandcentral
0.0425 USD/h 0.23 USD/h
UK South (GB) / uksouth
0.0408 USD/h 0.232 USD/h
UK West (GB) / ukwest
0.0429 USD/h 0.232 USD/h
West US (US) / westus
0.0432 USD/h 0.234 USD/h
Qatar Central (QA) / qatarcentral
0.0434 USD/h 0.235 USD/h
West Europe (NL) / westeurope
0.0444 USD/h 0.24 USD/h
UAE North (AE) / uaenorth
0.0445 USD/h 0.24 USD/h
Korea Central (KR) / koreacentral
0.0455 USD/h 0.246 USD/h
West India (IN) / westindia
0.0455 USD/h 0.246 USD/h
Australia Central 2 (AU) / australiacentral2
0.025 USD/h 0.25 USD/h
Australia Central (AU) / australiacentral
0.0462 USD/h 0.25 USD/h
Australia East (AU) / australiaeast
0.0462 USD/h 0.25 USD/h
Australia Southeast (AU) / australiasoutheast
0.0462 USD/h 0.25 USD/h
Southeast Asia (SG) / southeastasia
0.0462 USD/h 0.25 USD/h
New Zealand North (NZ) / newzealandnorth
0.0466 USD/h 0.252 USD/h
South Africa North (ZA) / southafricanorth
0.0469 USD/h 0.254 USD/h
Japan East (JP) / japaneast
0.0477 USD/h 0.258 USD/h
Japan West (JP) / japanwest
0.0477 USD/h 0.258 USD/h
East Asia (HK) / eastasia
0.0488 USD/h 0.264 USD/h
Norway East (NO) / norwayeast
0.0488 USD/h 0.264 USD/h
Switzerland North (CH) / switzerlandnorth
0.0488 USD/h 0.264 USD/h
South India (IN) / southindia
0.0501 USD/h 0.271 USD/h
India South Central (IN) / indiasouthcentral
0.0523 USD/h 0.283 USD/h
France South (FR) / francesouth
0.0538 USD/h 0.291 USD/h
Germany North (DE) / germanynorth
0.0553 USD/h 0.299 USD/h
UAE Central (AE) / uaecentral
0.0577 USD/h 0.312 USD/h
South Africa West (ZA) / southafricawest
0.0588 USD/h 0.3175 USD/h
Brazil South (BR) / brazilsouth
0.0588 USD/h 0.318 USD/h
Switzerland West (CH) / switzerlandwest
0.0634 USD/h 0.3428 USD/h
Norway West (NO) / norwaywest
0.0634 USD/h 0.343 USD/h
Brazil Southeast (US) / brazilsoutheast
0.0763 USD/h 0.413 USD/h

Processor

vCPUs
4
Hypervisor
Microsoft Hyper-V
CPU Allocation
Dedicated
CPU Cores
2
CPU Speed
2.3 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU Model
E5-2673 v4
CPU L1D Cache
48 KiB
CPU L1D Cache Total
96 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
64 KiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
3 MiB
CPU L3 Cache
48 MiB
CPU L3 Cache Total
48 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, rdseed, adx, smap, xsaveopt, vnmi, md_clear
Ecpus
2.6
Scalability
65

System Resources and Accelerators

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

    CPU and System Topology

    Server Description

    A balanced general-purpose virtual machine with dedicated legacy Intel processors and local SSD storage for lightweight utility workloads.

    General Purpose

    Microsoft Azure D4s_v3 is a general-purpose virtual machine from the DSv3 family, featuring an Intel Xeon E5-2673 v4 processor running at 2.3 GHz. It provides 4 vCPUs across 2 physical cores, 16.0 GB of RAM, and a 33 GB local SSD, with Premium Storage capability and no GPU. Benchmark evaluations place the instance's CPU and memory bandwidth performance mostly in the bottom 10% to 25%, though its PassMark memory score and small-model LLM text generation reach average tiers. Due to these performance constraints, the D4s_v3 is best suited for low-intensity workloads, such as basic web serving, development testing, and lightweight database operations, offering a balanced resource ratio for non-critical applications.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    0.25Score
    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) 332,239 ops/sec 1,921,522 ops/sec 0.17 50.00% 50.00% -59.00%
    Redis RPS (pipeline=16, SET) 1,928,928 ops/sec 11,803,344 ops/sec 0.16 20.00% 20.00% -31.00%
    PassMark Memory Mark (composite) 1,984 2,406 0.83 10.00% 10.00% -1.80%
    Memory bandwidth (read, 16 MB ~ L3) 40,309 MB/sec 108,665 MB/sec 0.36 10.00% 10.00% -9.70%
    PassMark single-thread CPU 1,777 Mops/s 2,365 Mops/s 0.75 10.00% 10.00% -2.80%

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 766

    Geekbench Multi-Core

    Score: 1,595

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 3,945
    Compression
    		 49,311
    Encryption
    		 1,507
    Extended Instructions
    		 3,383
    Floating Point Maths
    		 5,868
    Integer Maths
    		 10,957
    Physics
    		 511
    Prime Numbers
    		 25
    Single Threaded
    		 1,777
    String Sorting
    		 5,819

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 1,984
    Database Operations
    		 1,348
    Memory Latency
    		 50
    Memory Read Cached
    		 21,565
    Memory Read Uncached
    		 11,404
    Memory Write
    		 9,262

    Stress-ng Stressors

    CPU integerSingleMultiScaling
    atomic
    		 237.53 243.64 1.03×
    bitops
    		 93,148 188,151 2.02×
    branch
    		 98,120 308,514 3.14×
    funccall
    		 452.28 938.55 2.08×
    funcret
    		 8,569 24,540 2.86×
    hash
    		 107,559 307,281 2.86×
    intmath
    		 43,503 106,171 2.44×
    nop
    		 133,843 235,005 1.76×
    prime
    		 287,193 621,962 2.17×
    rotate
    		 69,842 148,369 2.12×
    str
    		 634,653 1,296,471 2.04×
    wcs
    		 446,091 762,064 1.71×
    CryptographySingleMultiScaling
    crypt
    		 2,025 3,738 1.85×
    CompressionSingleMultiScaling
    jpeg
    		 493.74 1,267 2.57×
    zlib
    		 39.94 135.19 3.38×
    HypervisorSingleMultiScaling
    clock
    		 17,671 44,183 2.50×
    clone
    		 1,076 2,432 2.26×
    context
    		 1,510 3,929 2.60×
    cpu-sched
    		 56.68 268.59 4.74×
    eventfd
    		 29,681 197,635 6.66×
    fault
    		 9,656 22,914 2.37×
    fork
    		 3,814 9,541 2.50×
    getrandom
    		 34,392 78,261 2.28×
    hrtimers
    		 298,543 393,861 1.32×
    mprotect
    		 476,514 506,818 1.06×
    mtx
    		 12,931,008 86,176,734 6.66×
    munmap
    		 2,846 7,218 2.54×
    null
    		 160,872 401,509 2.50×
    pipe
    		 676,707 1,167,541 1.73×
    priv-instr
    		 347,018 880,921 2.54×
    resched
    		 495,802 192,609 0.39×
    switch
    		 55,975 549,512 9.82×
    timermix
    		 147,250 464,712 3.16×
    tlb-shootdown
    		 5,811 7,063 1.22×
    tsc
    		 638,080 1,742,050 2.73×
    usersyscall
    		 244,586 618,036 2.53×
    vdso
    		 65,391,841 149,994,641 2.29×
    vfork
    		 22,868 73,040 3.19×
    x86syscall
    		 1,806,851 4,527,126 2.51×
    yield
    		 1,579,212 1,521,105 0.96×
    zero
    		 1,370,252 3,207,467 2.34×
    CPU float/SIMDSingleMultiScaling
    eigen
    		 10,561 26,982 2.55×
    expmath
    		 2,063 5,989 2.90×
    fma
    		 485,515 1,668,849 3.44×
    fp
    		 136.8 292.13 2.14×
    fractal
    		 3.6 10.6 2.94×
    hyperbolic
    		 2,200 6,418 2.92×
    logmath
    		 3,466 9,950 2.87×
    matrix
    		 2,692 7,753 2.88×
    matrix-3d
    		 625.13 1,054 1.69×
    monte-carlo
    		 85.28 214.98 2.52×
    mpfr
    		 1,005 2,143 2.13×
    powmath
    		 1,206 3,555 2.95×
    trig
    		 1,407 3,540 2.52×
    veccmp
    		 14,803 27,777 1.88×
    vecfp
    		 1,090 2,849 2.61×
    vecmath
    		 2,347 6,616 2.82×
    vecshuf
    		 474.42 1,027 2.16×
    vecwide
    		 22,722 52,149 2.30×
    AlgorithmsSingleMultiScaling
    bitonicsort
    		 5.8 11.2 1.93×
    bsearch
    		 177.28 444.34 2.51×
    bubblesort
    		 0.6 0.8 1.33×
    fibsearch
    		 206.91 490.75 2.37×
    heapsort
    		 6.6 15.4 2.33×
    hsearch
    		 5,057 11,607 2.30×
    insertionsort
    		 7.4 8.8 1.19×
    malloc
    		 1,787,366 7,409,818 4.15×
    mcontend
    		 149.04 625.27 4.20×
    mergesort
    		 19.2 53.4 2.78×
    qsort
    		 14.6 31 2.12×
    skiplist
    		 3,886 11,221 2.89×
    tree
    		 1.2 3.2 2.67×
    MemorySingleMultiScaling
    cache
    		 300,972 386,966 1.29×
    cachehammer
    		 356,568 1,266,437 3.55×
    cacheline
    		 28.74 113.98 3.97×
    l1cache
    		 645.62 553.17 0.86×
    memcpy
    		 290.12 569.56 1.96×
    memrate
    		 1.56 3.64 2.33×
    memthrash
    		 61.58 166.54 2.70×
    ptr-chase
    		 15,975,965 48,126,375 3.01×
    spinmem
    		 313.98 102.37 0.33×
    stream
    		 37.98 352.24 9.27×
    vm
    		 57,283 214,600 3.75×

    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

    PostgreSQL heavy read-only throughput

    Alternatives

    Servers of the Same Family

    INSTANCEvCPUsMEMORYAccelerators

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYAccelerators

    D4s_v3 FAQs