E48ps_v6 by Microsoft Azure

E48ps_v6 is a Epsv6 family [ARM processor] [Premium Storage capable] 48 vCPUs server offered by Microsoft Azure with 48 vCPUs, 384 GiB of memory and 0 GB of storage. The pricing starts at 0.2687 USD per hour.
48 vCPU
384 GiB Memory
Spare SCore
99,340
(All-cores)
2,075
(Single-core)

Specifications

Server Metadata

Vendor ID
azure
Server ID
Standard_E48ps_v6
Name
E48ps_v6
API Reference
Standard_E48ps_v6
Description
Epsv6 family [ARM processor] [Premium Storage capable] 48 vCPUs
Family
Epsv6
Hw Virt
Average Time To Start
20
Status
active
Observed At
2026-10-27T07:07:06.392506

Availability

REGION / IDSPOTONDEMAND
Central India (IN) / centralindia
0.2687 USD/h 1.454 USD/h
East US 2 (US) / eastus2
0.409 USD/h 2.213 USD/h
North Central US (US) / northcentralus
0.409 USD/h 2.213 USD/h
West US 2 (US) / westus2
0.409 USD/h 2.213 USD/h
West US 3 (US) / westus3
0.409 USD/h 2.213 USD/h
East US (US) / eastus
0.9806 USD/h 2.213 USD/h
Sweden Central (SE) / swedencentral
0.4356 USD/h 2.357 USD/h
Mexico Central (ZA) / mexicocentral
0.4498 USD/h 2.434 USD/h
Canada Central (CA) / canadacentral
0.4542 USD/h 2.458 USD/h
Canada East (CA) / canadaeast
0.4542 USD/h 2.458 USD/h
Spain Central (ES) / spaincentral
0.4568 USD/h 2.472 USD/h
North Europe (IE) / northeurope
0.6719 USD/h 2.472 USD/h
Central US (US) / centralus
0.4847 USD/h 2.501 USD/h
UK South (GB) / uksouth
0.4086 USD/h 2.549 USD/h
Italy North (IT) / italynorth
0.4755 USD/h 2.573 USD/h
France Central (FR) / francecentral
0.4781 USD/h 2.587 USD/h
West US (US) / westus
0.4781 USD/h 2.587 USD/h
Indonesia Central (ID) / indonesiacentral
0.4784 USD/h 2.589 USD/h
Germany West Central (DE) / germanywestcentral
0.4888 USD/h 2.645 USD/h
Poland Central (PL) / polandcentral
0.4888 USD/h 2.645 USD/h
West Europe (NL) / westeurope
0.5187 USD/h 2.645 USD/h
South Central US (US) / southcentralus
0.4905 USD/h 2.654 USD/h
West Central US (US) / westcentralus
0.4905 USD/h 2.654 USD/h
UK West (GB) / ukwest
0.4949 USD/h 2.678 USD/h
UAE North (AE) / uaenorth
0.4993 USD/h 2.702 USD/h
Australia East (AU) / australiaeast
0.51 USD/h 2.76 USD/h
Southeast Asia (SG) / southeastasia
0.51 USD/h 2.76 USD/h
Japan East (JP) / japaneast
0.5259 USD/h 2.846 USD/h
Japan West (JP) / japanwest
0.5269 USD/h 2.851 USD/h
Australia Southeast (AU) / australiasoutheast
0.5313 USD/h 2.875 USD/h
Austria East (AT) / austriaeast
0.5754 USD/h 2.877 USD/h
Belgium Central (BE) / belgiumcentral
0.5754 USD/h 2.877 USD/h
Denmark East (DK) / denmarkeast
0.5754 USD/h 2.877 USD/h
Korea Central (KR) / koreacentral
0.5331 USD/h 2.885 USD/h
New Zealand North (NZ) / newzealandnorth
0.5348 USD/h 2.894 USD/h
East Asia (HK) / eastasia
0.5623 USD/h 3.043 USD/h
South Africa North (ZA) / southafricanorth
0.5731 USD/h 3.101 USD/h
Norway East (NO) / norwayeast
0.5845 USD/h 3.163 USD/h
South India (IN) / southindia
0.6682 USD/h 3.341 USD/h
Switzerland North (CH) / switzerlandnorth
0.6377 USD/h 3.451 USD/h
Brazil South (BR) / brazilsouth
0.6501 USD/h 3.518 USD/h
South Africa West (ZA) / southafricawest
0.7442 USD/h 4.027 USD/h
Switzerland West (CH) / switzerlandwest
0.7606 USD/h 4.116 USD/h
UAE Central (AE) / uaecentral
0.8232 USD/h 4.116 USD/h

Processor

vCPUs
48
Hypervisor
Microsoft Hyper-V
CPU Allocation
Dedicated
CPU Cores
48
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
3 MiB
CPU L1I Cache
64 KiB
CPU L1I Cache Total
3 MiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
48 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
47.9
Scalability
99.79

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
    0 GB
    Storages
      NETWORK
      Inbound Traffic
      0 GB/month
      Outbound Traffic
      0 GB/month
      IPv4
      0

      CPU and System Topology

      Server Description

      An ARM-powered, memory-optimized virtual machine featuring forty-eight dedicated cores and exceptional memory bandwidth for high-throughput database workloads.

      Memory OptimizedStorage & DatabaseGeneral Purpose

      Microsoft Azure E48ps_v6 is an ARM-based, memory-optimized virtual machine from the Epsv6 family, running on Microsoft Hyper-V. It is configured with 48 dedicated physical cores utilizing the 3.4 GHz Microsoft ARM Neoverse-N2 processor, paired with 384.0 GB of RAM, yielding an 8.0 GB per core ratio. The instance lacks local storage and GPUs but supports Premium Storage. Benchmarks reveal top-tier memory performance, with uncached large-block read bandwidth at 463.87 GB/sec and exceptional database processing capabilities, including 89.22 million Redis SET operations per second. Multi-core performance is strong, though single-core metrics and large LLM inference speeds represent relative performance tradeoffs. This server is highly efficient for memory-intensive workloads such as in-memory databases, caching layers, software compilation, and high-throughput web serving.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      3.4Score
      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) 8,609,974 ops/sec 1,918,343 ops/sec 4.5 50.00% 50.00% +110.00%
      Redis RPS (pipeline=16, SET) 55,318,801 ops/sec 11,704,734 ops/sec 4.6 20.00% 20.00% +36.00%
      PassMark Memory Mark (composite) 3,403 2,416 1.4 10.00% 10.00% +3.40%
      Memory bandwidth (read, 16 MB ~ L3) 545,637 MB/sec 108,420 MB/sec 5 10.00% 10.00% +17.00%
      PassMark single-thread CPU 1,880 Mops/s 2,365 Mops/s 0.79 10.00% 10.00% -2.30%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,692

      Geekbench Multi-Core

      Score: 21,904

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 36,270
      Compression
      		 332,553
      Encryption
      		 9,013
      Extended Instructions
      		 42,879
      Floating Point Maths
      		 254,158
      Integer Maths
      		 302,482
      Physics
      		 13,081
      Prime Numbers
      		 532
      Single Threaded
      		 1,880
      String Sorting
      		 243,549

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 3,403
      Database Operations
      		 37,055
      Memory Latency
      		 52
      Memory Read Cached
      		 25,607
      Memory Read Uncached
      		 19,077
      Memory Write
      		 25,741

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 187.85 22.38 0.12×
      bitops
      		 151,382 7,249,461 47.89×
      branch
      		 256,673 12,299,213 47.92×
      funccall
      		 1,906 91,298 47.90×
      funcret
      		 33,055 1,582,688 47.88×
      hash
      		 177,620 8,511,730 47.92×
      intmath
      		 38,887 1,872,460 48.15×
      nop
      		 456,807 21,902,557 47.95×
      prime
      		 488,237 23,354,395 47.83×
      rotate
      		 130,946 6,266,006 47.85×
      str
      		 696,389 33,338,208 47.87×
      wcs
      		 218,098 10,432,646 47.83×
      CryptographySingleMultiScaling
      crypt
      		 3,841 183,950 47.89×
      CompressionSingleMultiScaling
      jpeg
      		 689.92 32,785 47.52×
      zlib
      		 42.16 2,211 52.44×
      HypervisorSingleMultiScaling
      clock
      		 28,447 300,594 10.57×
      clone
      		 294.52 5,868 19.92×
      context
      		 2,742 132,912 48.47×
      cpu-sched
      		 69.97 3,046 43.53×
      eventfd
      		 58,328 1,318,677 22.61×
      fault
      		 22,098 345,144 15.62×
      fork
      		 3,937 68,672 17.44×
      getrandom
      		 59,934 2,873,235 47.94×
      hrtimers
      		 999,782 4,721,572 4.72×
      mprotect
      		 1,078,514 17,265,579 16.01×
      mtx
      		 9,439,826 2,198,130,108 232.86×
      munmap
      		 2,870 73,184 25.50×
      null
      		 482,950 23,322,823 48.29×
      pipe
      		 851,510 26,008,039 30.54×
      priv-instr
      		 835,835 9,489,183 11.35×
      resched
      		 1,859,859 6,379,142 3.43×
      switch
      		 70,869 23,951,385 337.97×
      timermix
      		 623,316 30,030,627 48.18×
      tlb-shootdown
      		 15,307 238,128 15.56×
      vdso
      		 46,697,257 2,212,066,826 47.37×
      vfork
      		 30,192 278,968 9.24×
      yield
      		 61,817,977 74,138,361 1.20×
      zero
      		 2,762,393 132,959,474 48.13×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 2,130 102,041 47.90×
      expmath
      		 393.47 18,837 47.87×
      fma
      		 769,132 36,774,621 47.81×
      fp
      		 160.75 7,724 48.05×
      fractal
      		 7.8 369.89 47.42×
      hyperbolic
      		 387.36 18,561 47.92×
      logmath
      		 465.53 22,309 47.92×
      matrix
      		 6,607 316,426 47.89×
      matrix-3d
      		 1,033 21,015 20.35×
      monte-carlo
      		 214.36 10,115 47.19×
      mpfr
      		 1,447 69,324 47.91×
      powmath
      		 272.33 13,047 47.91×
      trig
      		 521.15 24,960 47.89×
      veccmp
      		 19,427 930,312 47.89×
      vecfp
      		 913.24 43,807 47.97×
      vecmath
      		 4,876 233,447 47.88×
      vecshuf
      		 1,021 47,866 46.90×
      vecwide
      		 27,227 1,186,431 43.58×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 9.4 446.79 47.53×
      bsearch
      		 382.04 18,264 47.81×
      bubblesort
      		 1.2 57.6 48.00×
      fibsearch
      		 432.69 20,728 47.90×
      heapsort
      		 13.4 633.59 47.28×
      hsearch
      		 6,997 335,299 47.92×
      insertionsort
      		 7.8 367.4 47.10×
      malloc
      		 3,004,631 86,416,394 28.76×
      mcontend
      		 201.68 114,160 566.04×
      mergesort
      		 38 1,809 47.59×
      qsort
      		 24.4 1,171 48.01×
      skiplist
      		 7,040 337,914 48.00×
      tree
      		 1.4 40.92 29.23×
      MemorySingleMultiScaling
      cache
      		 456,845 1,785,781 3.91×
      cachehammer
      		 1,739,248 28,452,613 16.36×
      cacheline
      		 33.19 4,817 145.12×
      l1cache
      		 303.14 14,348 47.33×
      memcpy
      		 724.26 34,691 47.90×
      memrate
      		 5.13 67.3 13.12×
      memthrash
      		 212.34 369.57 1.74×
      ptr-chase
      		 18,806,001 394,972,972 21.00×
      spinmem
      		 4,371 43,106 9.86×
      stream
      		 26.69 18,800 704.37×
      vm
      		 123,531 3,673,103 29.73×

      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
      E2ps_v6 216 GiB0
      E4ps_v6 432 GiB0
      E8ps_v6 864 GiB0
      E16ps_v6 16128 GiB0
      E32ps_v6 32256 GiB0
      E64ps_v6 64512 GiB0
      E96ps_v6 96672 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      E48ps_v6 FAQs