E4pds_v5 by Microsoft Azure

E4pds_v5 is a EPDSv5 family [ARM processor] [Local Disk] [Premium Storage capable] 4 vCPUs server offered by Microsoft Azure with 4 vCPUs, 32 GiB of memory and 154 GB of storage. The pricing starts at 0.0303 USD per hour.
4 vCPU
32 GiB Memory
154 GB Storage
Spare SCore
7,253
(All-cores)
1,823
(Single-core)

Specifications

Server Metadata

Vendor ID
azure
Server ID
Standard_E4pds_v5
Name
E4pds_v5
API Reference
Standard_E4pds_v5
Description
EPDSv5 family [ARM processor] [Local Disk] [Premium Storage capable] 4 vCPUs
Family
EPDSv5
Hw Virt
Average Time To Start
18
Status
active
Observed At
2026-11-01T01:30:57.926040

Availability

REGION / IDSPOTONDEMAND
Central India (IN) / centralindia
0.0303 USD/h 0.164 USD/h
Jio India Central (IN) / jioindiacentral
- 0.164 USD/h
Jio India West (IN) / jioindiawest
- 0.164 USD/h
East US 2 (US) / eastus2
0.0425 USD/h 0.23 USD/h
North Central US (US) / northcentralus
0.0425 USD/h 0.23 USD/h
West US 2 (US) / westus2
0.0425 USD/h 0.23 USD/h
West US 3 (US) / westus3
0.0425 USD/h 0.23 USD/h
East US (US) / eastus
0.0486 USD/h 0.23 USD/h
Sweden Central (SE) / swedencentral
0.0449 USD/h 0.243 USD/h
Canada Central (CA) / canadacentral
0.0468 USD/h 0.253 USD/h
North Europe (IE) / northeurope
0.0473 USD/h 0.256 USD/h
Central US (US) / centralus
0.048 USD/h 0.26 USD/h
West US (US) / westus
0.048 USD/h 0.26 USD/h
France Central (FR) / francecentral
0.0499 USD/h 0.27 USD/h
UK South (GB) / uksouth
0.0476 USD/h 0.271 USD/h
Germany West Central (DE) / germanywestcentral
0.051 USD/h 0.276 USD/h
South Central US (US) / southcentralus
0.051 USD/h 0.276 USD/h
West Central US (US) / westcentralus
0.051 USD/h 0.276 USD/h
West Europe (NL) / westeurope
0.051 USD/h 0.276 USD/h
Australia East (AU) / australiaeast
0.0514 USD/h 0.278 USD/h
Japan East (JP) / japaneast
0.0514 USD/h 0.278 USD/h
Southeast Asia (SG) / southeastasia
0.0514 USD/h 0.278 USD/h
East Asia (HK) / eastasia
0.0519 USD/h 0.281 USD/h
Switzerland North (CH) / switzerlandnorth
0.0565 USD/h 0.306 USD/h

Processor

vCPUs
4
Hypervisor
Microsoft Hyper-V
CPU Allocation
Dedicated
CPU Cores
4
CPU Speed
3 GHz
CPU Architecture
arm64
CPU Manufacturer
Ampere
CPU Family
ARMv8
CPU Model
Neoverse-N1
CPU L1D Cache
64 KiB
CPU L1D Cache Total
256 KiB
CPU L1I Cache
64 KiB
CPU L1I Cache Total
256 KiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
4 MiB
CPU L3 Cache
32 MiB
CPU L3 Cache Total
32 MiB
CPU Flags
fp, asimd, evtstrm, aes, pmull, sha1, sha2, crc32, atomics, fphp, asimdhp, cpuid, asimdrdm, lrcpc, dcpop, asimddp
Ecpus
4
Scalability
100

System Resources and Accelerators

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

    CPU and System Topology

    Server Description

    An energy-efficient ARM-based virtual machine featuring high memory density and local SSD storage for database and caching workloads.

    Memory OptimizedGeneral PurposeStorage & Database

    Microsoft Azure E4pds_v5 is an ARM-based virtual machine from the EPDSv5 family, powered by a dedicated 4-core Ampere Altra ARMv8 Neoverse-N1 processor running at 3.0 GHz. It features 32.0 GB of RAM, providing a high 8.0 GB per vCPU ratio, alongside a 154 GB local SSD. Operating under the Microsoft Hyper-V hypervisor, this instance delivers average CPU performance, with stress-ng single-core and multi-core scores of 1822.68 and 7252.56. While database operations perform at an average tier, cryptographic and LLM inference capabilities are weak to poor due to the absence of advanced vector and matrix extensions. Qualitatively, the server offers high memory density on an energy-efficient ARM architecture, making it a cost-effective choice for memory-optimized workloads. It is best suited for database hosting, caching, and moderate web serving rather than compute-intensive tasks.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    0.33Score
    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) 508,843 ops/sec 1,918,343 ops/sec 0.27 50.00% 50.00% -48.00%
    Redis RPS (pipeline=16, SET) 2,903,528 ops/sec 11,704,734 ops/sec 0.24 20.00% 20.00% -25.00%
    PassMark Memory Mark (composite) 1,810 2,416 0.75 10.00% 10.00% -2.80%
    Memory bandwidth (read, 16 MB ~ L3) 51,431 MB/sec 108,466 MB/sec 0.46 10.00% 10.00% -7.50%
    PassMark single-thread CPU 1,333 Mops/s 2,365 Mops/s 0.54 10.00% 10.00% -6.00%

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 1,056

    Geekbench Multi-Core

    Score: 3,519

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 3,214
    Compression
    		 21,958
    Encryption
    		 650
    Extended Instructions
    		 2,983
    Floating Point Maths
    		 14,351
    Integer Maths
    		 18,770
    Physics
    		 738
    Prime Numbers
    		 37
    Single Threaded
    		 1,333
    String Sorting
    		 13,738

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 1,810
    Database Operations
    		 2,893
    Memory Latency
    		 69
    Memory Read Cached
    		 11,381
    Memory Read Uncached
    		 9,387
    Memory Write
    		 15,010

    Stress-ng Stressors

    CPU integerSingleMultiScaling
    atomic
    		 86.12 92.62 1.08×
    bitops
    		 108,475 431,737 3.98×
    branch
    		 220,848 880,122 3.99×
    funccall
    		 1,338 5,318 3.97×
    funcret
    		 20,718 82,672 3.99×
    hash
    		 128,193 509,230 3.97×
    intmath
    		 30,933 125,667 4.06×
    nop
    		 173,672 690,083 3.97×
    prime
    		 336,786 1,338,637 3.97×
    rotate
    		 96,536 383,558 3.97×
    str
    		 514,829 2,046,038 3.97×
    wcs
    		 119,210 473,855 3.97×
    CryptographySingleMultiScaling
    crypt
    		 2,899 11,563 3.99×
    CompressionSingleMultiScaling
    jpeg
    		 524.82 2,077 3.96×
    zlib
    		 38.97 142.6 3.66×
    HypervisorSingleMultiScaling
    clock
    		 24,797 84,750 3.42×
    clone
    		 240.82 620.32 2.58×
    context
    		 2,609 10,363 3.97×
    cpu-sched
    		 64.54 249.63 3.87×
    eventfd
    		 54,876 271,360 4.94×
    fault
    		 13,076 45,708 3.50×
    fork
    		 4,184 13,833 3.31×
    getrandom
    		 49,143 195,232 3.97×
    hrtimers
    		 123,342 487,415 3.95×
    mprotect
    		 1,018,135 1,362,893 1.34×
    mtx
    		 8,268,674 191,224,523 23.13×
    munmap
    		 2,884 9,976 3.46×
    null
    		 462,974 1,837,677 3.97×
    pipe
    		 924,956 2,527,833 2.73×
    priv-instr
    		 739,161 2,768,366 3.75×
    resched
    		 1,347,975 537,988 0.40×
    switch
    		 100,868 1,103,231 10.94×
    timermix
    		 401,271 1,591,929 3.97×
    tlb-shootdown
    		 4,623 5,547 1.20×
    vdso
    		 46,821,795 185,993,080 3.97×
    vfork
    		 27,722 70,453 2.54×
    yield
    		 3,264,491 3,278,584 1.00×
    zero
    		 2,078,877 8,236,317 3.96×
    CPU float/SIMDSingleMultiScaling
    eigen
    		 1,336 5,307 3.97×
    expmath
    		 240.09 954.29 3.97×
    fma
    		 641,198 2,547,880 3.97×
    fp
    		 103.2 410.07 3.97×
    fractal
    		 6.6 25.8 3.91×
    hyperbolic
    		 244.32 971.06 3.97×
    logmath
    		 293.69 1,168 3.98×
    matrix
    		 5,349 21,230 3.97×
    matrix-3d
    		 489.74 1,778 3.63×
    monte-carlo
    		 192.96 771.28 4.00×
    mpfr
    		 642.01 2,549 3.97×
    powmath
    		 176.52 701.66 3.97×
    trig
    		 329.65 1,310 3.97×
    veccmp
    		 17,168 68,229 3.97×
    vecfp
    		 744.74 2,964 3.98×
    vecmath
    		 3,090 12,284 3.97×
    vecshuf
    		 671.88 2,668 3.97×
    vecwide
    		 18,403 73,165 3.98×
    AlgorithmsSingleMultiScaling
    bitonicsort
    		 5.4 21.6 4.00×
    bsearch
    		 258.33 1,028 3.98×
    bubblesort
    		 0.8 3 3.75×
    fibsearch
    		 273.57 1,086 3.97×
    heapsort
    		 8.2 32.8 4.00×
    hsearch
    		 4,917 19,491 3.96×
    insertionsort
    		 4.6 18.2 3.96×
    malloc
    		 2,404,552 10,009,597 4.16×
    mcontend
    		 298.53 7,216 24.17×
    mergesort
    		 27.8 108.99 3.92×
    qsort
    		 19.4 77.2 3.98×
    skiplist
    		 5,364 21,293 3.97×
    tree
    		 1 3.2 3.20×
    MemorySingleMultiScaling
    cache
    		 298,968 431,669 1.44×
    cachehammer
    		 123,229 310,455 2.52×
    cacheline
    		 38.51 171.04 4.44×
    l1cache
    		 182.39 724.18 3.97×
    memcpy
    		 443.71 1,763 3.97×
    memrate
    		 3.15 10.23 3.25×
    memthrash
    		 100.87 100.37 1.00×
    ptr-chase
    		 10,615,922 39,613,681 3.73×
    spinmem
    		 699.57 393.37 0.56×
    stream
    		 62.49 801.5 12.83×
    vm
    		 58,459 264,813 4.53×

    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
    E2pds_v5 216 GiB0
    E8pds_v5 864 GiB0
    E16pds_v5 16128 GiB0
    E20pds_v5 20160 GiB0
    E32pds_v5 32208 GiB0

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYAccelerators

    E4pds_v5 FAQs