E20a_v4 by Microsoft Azure

E20a_v4 is a EAv4 family [AMD processor] 20 vCPUs server offered by Microsoft Azure with 20 vCPUs, 160 GiB of memory and 512 GB of storage. The pricing starts at 0.1467 USD per hour.
20 vCPU
160 GiB Memory
512 GB Storage
Spare SCore
7,696
(All-cores)
767
(Single-core)

Specifications

Server Metadata

Vendor ID
azure
Server ID
Standard_E20a_v4
Name
E20a_v4
API Reference
Standard_E20a_v4
Description
EAv4 family [AMD processor] 20 vCPUs
Family
EAv4
Hw Virt
Average Time To Start
20
Status
active
Observed At
2026-10-29T17:27:48.786004

Availability

REGION / IDSPOTONDEMAND
Central India (IN) / centralindia
0.1467 USD/h 0.794 USD/h
Jio India Central (IN) / jioindiacentral
- 0.794 USD/h
Jio India West (IN) / jioindiawest
- 0.794 USD/h
East US 2 (US) / eastus2
0.2328 USD/h 1.26 USD/h
North Central US (US) / northcentralus
0.2328 USD/h 1.26 USD/h
West US 2 (US) / westus2
0.2328 USD/h 1.26 USD/h
West US 3 (US) / westus3
0.2328 USD/h 1.26 USD/h
East US (US) / eastus
0.2652 USD/h 1.26 USD/h
India South Central (IN) / indiasouthcentral
0.2402 USD/h 1.3 USD/h
Spain Central (ES) / spaincentral
0.2458 USD/h 1.33 USD/h
Sweden Central (SE) / swedencentral
0.2476 USD/h 1.34 USD/h
Indonesia Central (ID) / indonesiacentral
0.2513 USD/h 1.36 USD/h
Malaysia West (MY) / malaysiawest
0.2528 USD/h 1.368 USD/h
Austria East (AT) / austriaeast
0.2532 USD/h 1.37 USD/h
Belgium Central (BE) / belgiumcentral
0.2532 USD/h 1.37 USD/h
Denmark East (DK) / denmarkeast
0.2532 USD/h 1.37 USD/h
Canada Central (CA) / canadacentral
0.255 USD/h 1.38 USD/h
Canada East (CA) / canadaeast
0.255 USD/h 1.38 USD/h
Mexico Central (ZA) / mexicocentral
0.2561 USD/h 1.386 USD/h
West US (US) / westus
0.2587 USD/h 1.4 USD/h
North Europe (IE) / northeurope
0.2606 USD/h 1.41 USD/h
Central US (US) / centralus
0.263 USD/h 1.424 USD/h
Korea South (KR) / koreasouth
0.2661 USD/h 1.44 USD/h
UK South (GB) / uksouth
0.2364 USD/h 1.48 USD/h
France Central (FR) / francecentral
0.2735 USD/h 1.48 USD/h
Israel Central (IL) / israelcentral
0.2735 USD/h 1.48 USD/h
Italy North (IT) / italynorth
0.2735 USD/h 1.48 USD/h
Australia Central 2 (AU) / australiacentral2
0.151 USD/h 1.51 USD/h
Australia Central (AU) / australiacentral
0.279 USD/h 1.51 USD/h
Australia East (AU) / australiaeast
0.279 USD/h 1.51 USD/h
South Central US (US) / southcentralus
0.2794 USD/h 1.512 USD/h
West Central US (US) / westcentralus
0.2794 USD/h 1.512 USD/h
Germany West Central (DE) / germanywestcentral
0.2809 USD/h 1.52 USD/h
Japan East (JP) / japaneast
0.2809 USD/h 1.52 USD/h
Japan West (JP) / japanwest
0.2809 USD/h 1.52 USD/h
Korea Central (KR) / koreacentral
0.2809 USD/h 1.52 USD/h
Poland Central (PL) / polandcentral
0.2809 USD/h 1.52 USD/h
Southeast Asia (SG) / southeastasia
0.2809 USD/h 1.52 USD/h
West Europe (NL) / westeurope
0.2809 USD/h 1.52 USD/h
UK West (GB) / ukwest
0.2818 USD/h 1.525 USD/h
Qatar Central (QA) / qatarcentral
0.2866 USD/h 1.551 USD/h
UAE North (AE) / uaenorth
0.2866 USD/h 1.551 USD/h
Chile Central (CL) / chilecentral
0.2924 USD/h 1.582 USD/h
New Zealand North (NZ) / newzealandnorth
0.3224 USD/h 1.586 USD/h
West India (IN) / westindia
0.2981 USD/h 1.613 USD/h
Australia Southeast (AU) / australiasoutheast
0.3027 USD/h 1.638 USD/h
East Asia (HK) / eastasia
0.3086 USD/h 1.67 USD/h
South Africa North (ZA) / southafricanorth
0.3105 USD/h 1.68 USD/h
South India (IN) / southindia
0.3284 USD/h 1.777 USD/h
Norway East (NO) / norwayeast
0.333 USD/h 1.802 USD/h
Switzerland North (CH) / switzerlandnorth
0.333 USD/h 1.802 USD/h
France South (FR) / francesouth
0.3556 USD/h 1.924 USD/h
Germany North (DE) / germanynorth
0.3652 USD/h 1.976 USD/h
Brazil South (BR) / brazilsouth
0.3714 USD/h 2.01 USD/h
UAE Central (AE) / uaecentral
0.3726 USD/h 2.016 USD/h
South Africa West (ZA) / southafricawest
0.4036 USD/h 2.184 USD/h
Norway West (NO) / norwaywest
0.4328 USD/h 2.342 USD/h
Switzerland West (CH) / switzerlandwest
0.4328 USD/h 2.342 USD/h
Brazil Southeast (US) / brazilsoutheast
0.4829 USD/h 2.613 USD/h

Processor

vCPUs
20
Hypervisor
Microsoft Hyper-V
CPU Allocation
Dedicated
CPU Cores
10
CPU Speed
3.35 GHz
CPU Architecture
x86_64
CPU Manufacturer
AMD
CPU Family
EPYC
CPU Model
7763
CPU L1D Cache
32 KiB
CPU L1D Cache Total
320 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
320 KiB
CPU L2 Cache
512 KiB
CPU L2 Cache Total
5 MiB
CPU L3 Cache
16 MiB
CPU L3 Cache Total
80 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, ht, syscall, nx, mmxext, fxsr_opt, pdpe1gb, rdtscp, lm, rep_good, nopl, cpuid, extd_apicid, pni, pclmulqdq, ssse3, fma, cx16, sse4_1, sse4_2, movbe, popcnt, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, cmp_legacy, cr8_legacy, abm, sse4a, misalignsse, 3dnowprefetch, osvw, topoext, vmmcall, fsgsbase, bmi1, avx2, smep, bmi2, erms, rdseed, adx, smap, clflushopt, clwb, sha_ni, xsaveopt, xsavec, xgetbv1, xsaves, xsaveerptr, arat, umip, vaes, vpclmulqdq, rdpid, fsrm
Ecpus
10
Scalability
50

System Resources and Accelerators

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

    CPU and System Topology

    Server Description

    An x86_64 server featuring high memory density, dedicated AMD EPYC processing, and bundled SSD storage for memory-intensive workloads.

    Memory OptimizedGeneral Purpose

    The Microsoft Azure E20a_v4 is an x86_64 memory-optimized server from the EAv4 family, powered by a dedicated AMD EPYC 7763 processor running at 3.35 GHz. It features 20 vCPUs, 160.0 GB of RAM, and a bundled 512 GB SSD. Operating under Microsoft Hyper-V, this instance delivers a high memory-to-vCPU ratio of 8.0 GB. Benchmark results show strong memory performance, with a PassMark memory score in the top 25 percent, alongside average multi-core and database performance, though single-core CPU throughput is relatively weak. Lacking a GPU, it is not designed for heavy AI generation but excels in memory-intensive environments. The E20a_v4 is highly suited for database hosting, caching layers, and memory-heavy enterprise applications.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    0.91Score
    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) 1,565,355 ops/sec 1,919,289 ops/sec 0.84 50.00% 50.00% -8.30%
    Redis RPS (pipeline=16, SET) 11,744,104 ops/sec 11,728,058 ops/sec 1 20.00% 20.00% 0.00%
    PassMark Memory Mark (composite) 2,787 2,416 1.2 10.00% 10.00% +1.80%
    Memory bandwidth (read, 16 MB ~ L3) 98,581 MB/sec 108,466 MB/sec 0.9 10.00% 10.00% -1.00%
    PassMark single-thread CPU 2,105 Mops/s 2,365 Mops/s 0.88 10.00% 10.00% -1.30%

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 1,594

    Geekbench Multi-Core

    Score: 11,374

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 24,051
    Compression
    		 298,504
    Encryption
    		 21,223
    Extended Instructions
    		 17,595
    Floating Point Maths
    		 39,998
    Integer Maths
    		 67,302
    Physics
    		 2,785
    Prime Numbers
    		 177
    Single Threaded
    		 2,105
    String Sorting
    		 39,165

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 2,787
    Database Operations
    		 6,826
    Memory Latency
    		 51
    Memory Read Cached
    		 24,678
    Memory Read Uncached
    		 12,513
    Memory Write
    		 10,978

    Stress-ng Stressors

    CPU integerSingleMultiScaling
    atomic
    		 414.17 256.79 0.62×
    bitops
    		 118,521 1,488,216 12.56×
    branch
    		 153,991 2,610,826 16.95×
    funccall
    		 490.82 6,624 13.50×
    funcret
    		 13,837 209,001 15.10×
    hash
    		 132,999 2,010,383 15.12×
    intmath
    		 19,189 206,711 10.77×
    nop
    		 236,137 2,342,361 9.92×
    prime
    		 340,910 4,576,502 13.42×
    rotate
    		 58,731 611,688 10.42×
    str
    		 619,354 7,792,254 12.58×
    wcs
    		 478,920 5,282,291 11.03×
    CryptographySingleMultiScaling
    crypt
    		 2,770 29,660 10.71×
    CompressionSingleMultiScaling
    jpeg
    		 647.22 8,818 13.63×
    zlib
    		 48.99 909.71 18.57×
    HypervisorSingleMultiScaling
    clock
    		 3,743 41,073 10.97×
    clone
    		 687.17 7,107 10.34×
    context
    		 3,411 57,335 16.81×
    cpu-sched
    		 58.78 1,283 21.83×
    eventfd
    		 21,366 926,602 43.37×
    fault
    		 7,202 68,164 9.46×
    fork
    		 2,476 21,448 8.66×
    getrandom
    		 36,704 481,739 13.12×
    hrtimers
    		 65,334 713,900 10.93×
    mprotect
    		 332,999 3,164,915 9.50×
    mtx
    		 22,620,233 851,945,978 37.66×
    munmap
    		 1,800 18,847 10.47×
    null
    		 416,624 6,704,357 16.09×
    pipe
    		 1,704,348 6,348,784 3.73×
    priv-instr
    		 375,001 5,441,892 14.51×
    resched
    		 3,986,976 857,089 0.21×
    switch
    		 50,666 2,769,898 54.67×
    timermix
    		 41,535 785,758 18.92×
    tlb-shootdown
    		 7,112 42,666 6.00×
    tsc
    		 640,457 12,380,438 19.33×
    usersyscall
    		 295,658 4,447,114 15.04×
    vdso
    		 74,361,317 1,044,973,172 14.05×
    vfork
    		 13,228 90,699 6.86×
    x86syscall
    		 5,171,913 86,289,075 16.68×
    yield
    		 9,142,357 9,830,394 1.08×
    zero
    		 2,091,582 33,565,918 16.05×
    CPU float/SIMDSingleMultiScaling
    eigen
    		 12,208 142,952 11.71×
    expmath
    		 2,733 42,464 15.54×
    fma
    		 724,836 11,460,638 15.81×
    fp
    		 203.62 3,039 14.93×
    fractal
    		 6.4 97.67 15.26×
    hyperbolic
    		 3,586 53,652 14.96×
    logmath
    		 4,018 58,595 14.58×
    matrix
    		 2,606 48,007 18.42×
    matrix-3d
    		 63.98 1,331 20.80×
    monte-carlo
    		 192.57 3,002 15.59×
    mpfr
    		 1,278 16,145 12.63×
    powmath
    		 1,347 21,192 15.73×
    trig
    		 1,569 23,066 14.70×
    veccmp
    		 17,169 201,182 11.72×
    vecfp
    		 1,397 20,842 14.92×
    vecmath
    		 3,301 52,908 16.03×
    vecshuf
    		 475.29 5,827 12.26×
    vecwide
    		 26,653 301,904 11.33×
    AlgorithmsSingleMultiScaling
    bitonicsort
    		 7 85.6 12.23×
    bsearch
    		 226.05 2,782 12.31×
    bubblesort
    		 0.8 8 10.00×
    fibsearch
    		 252.97 3,229 12.76×
    heapsort
    		 8.4 117.99 14.05×
    hsearch
    		 5,335 65,612 12.30×
    insertionsort
    		 6.8 80.59 11.85×
    malloc
    		 2,060,589 18,300,189 8.88×
    mcontend
    		 55.1 1,782 32.34×
    mergesort
    		 26 386.18 14.85×
    qsort
    		 16.2 239.59 14.79×
    skiplist
    		 5,418 86,595 15.98×
    tree
    		 1.6 17.8 11.13×
    MemorySingleMultiScaling
    cache
    		 227,513 474,563 2.09×
    cachehammer
    		 240,352 3,238,092 13.47×
    cacheline
    		 29.76 548.14 18.42×
    l1cache
    		 197.05 1,889 9.59×
    memcpy
    		 353.06 3,598 10.19×
    memrate
    		 1.76 10.05 5.71×
    memthrash
    		 45.04 364.26 8.09×
    ptr-chase
    		 30,646,791 188,589,166 6.15×
    spinmem
    		 249.98 639.84 2.56×
    stream
    		 25.67 2,570 100.10×
    vm
    		 83,336 293,792 3.53×

    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
    E2a_v4 216 GiB0
    E4a_v4 432 GiB0
    E8a_v4 864 GiB0
    E16a_v4 16128 GiB0
    E32a_v4 32256 GiB0
    E48a_v4 48384 GiB0
    E64a_v4 64512 GiB0

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYAccelerators

    E20a_v4 FAQs