FX96-48ms_v2 by Microsoft Azure

FX96-48ms_v2 is a FXmsv2 family [Memory Intensive] [Premium Storage capable] [Intel processor] 96 vCPUs server offered by Microsoft Azure with 48 vCPUs, 1832 GiB of memory and 0 GB of storage. The pricing starts at 1.9631 USD per hour.
48 vCPU
1832 GiB Memory
Spare SCore
53,282
(All-cores)
2,169
(Single-core)

Specifications

Server Metadata

Vendor ID
azure
Server ID
Standard_FX96-48ms_v2
Name
FX96-48ms_v2
API Reference
Standard_FX96-48ms_v2
Description
FXmsv2 family [Memory Intensive] [Premium Storage capable] [Intel processor] 96 vCPUs
Family
FXmsv2
Hw Virt
Average Time To Start
24
Status
active
Observed At
2026-10-24T01:15:01.840354

Availability

REGION / IDSPOTONDEMAND
East US 2 (US) / eastus2
1.9631 USD/h 10.623 USD/h
West US 3 (US) / westus3
1.9631 USD/h 10.623 USD/h
East US (US) / eastus
2.2298 USD/h 10.623 USD/h
West US 2 (US) / westus2
1.9637 USD/h 10.626 USD/h
Central India (IN) / centralindia
2.0261 USD/h 10.964 USD/h
Canada Central (CA) / canadacentral
2.1601 USD/h 11.689 USD/h
Central US (US) / centralus
2.2159 USD/h 12.004 USD/h
Sweden Central (SE) / swedencentral
2.2394 USD/h 12.118 USD/h
Indonesia Central (ID) / indonesiacentral
2.2969 USD/h 12.429 USD/h
South Central US (US) / southcentralus
2.3558 USD/h 12.748 USD/h
West Central US (US) / westcentralus
2.3558 USD/h 12.748 USD/h
North Europe (IE) / northeurope
2.3566 USD/h 12.752 USD/h
Spain Central (ES) / spaincentral
2.3566 USD/h 12.752 USD/h
UK West (GB) / ukwest
2.3754 USD/h 12.854 USD/h
Qatar Central (QA) / qatarcentral
2.4157 USD/h 13.072 USD/h
UAE North (AE) / uaenorth
2.4157 USD/h 13.072 USD/h
France Central (FR) / francecentral
2.4743 USD/h 13.389 USD/h
UK South (GB) / uksouth
2.4743 USD/h 13.389 USD/h
Australia Southeast (AU) / australiasoutheast
2.5521 USD/h 13.81 USD/h
Austria East (AT) / austriaeast
2.5521 USD/h 13.81 USD/h
Belgium Central (BE) / belgiumcentral
2.5521 USD/h 13.81 USD/h
West US (US) / westus
2.5528 USD/h 13.814 USD/h
Chile Central (CL) / chilecentral
2.7483 USD/h 14.872 USD/h
Germany West Central (DE) / germanywestcentral
2.7493 USD/h 14.877 USD/h
West Europe (NL) / westeurope
2.7493 USD/h 14.877 USD/h
South India (IN) / southindia
2.7681 USD/h 14.979 USD/h
South Africa North (ZA) / southafricanorth
2.8043 USD/h 15.175 USD/h
Southeast Asia (SG) / southeastasia
2.8467 USD/h 15.404 USD/h
Australia East (AU) / australiaeast
2.8476 USD/h 15.409 USD/h
Japan East (JP) / japaneast
2.8476 USD/h 15.409 USD/h
Korea Central (KR) / koreacentral
2.8476 USD/h 15.409 USD/h
New Zealand North (NZ) / newzealandnorth
2.989 USD/h 16.174 USD/h
Switzerland North (CH) / switzerlandnorth
3.0243 USD/h 16.365 USD/h
Germany North (DE) / germanynorth
3.574 USD/h 19.34 USD/h
Brazil South (BR) / brazilsouth
3.8294 USD/h 20.722 USD/h

Processor

vCPUs
48
Hypervisor
Microsoft Hyper-V
CPU Allocation
Dedicated
CPU Cores
24
CPU Speed
4.2 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU Model
8573C
CPU L1D Cache
48 KiB
CPU L1D Cache Total
1 MiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
768 KiB
CPU L2 Cache
2 MiB
CPU L2 Cache Total
48 MiB
CPU L3 Cache
260 MiB
CPU L3 Cache Total
520 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, tsc_reliable, nonstop_tsc, cpuid, aperfmperf, tsc_known_freq, pni, pclmulqdq, vmx, ssse3, fma, cx16, pcid, sse4_1, sse4_2, x2apic, movbe, popcnt, tsc_deadline_timer, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, abm, 3dnowprefetch, tpr_shadow, ept, vpid, ept_ad, fsgsbase, tsc_adjust, bmi1, hle, avx2, smep, bmi2, erms, invpcid, rtm, avx512f, avx512dq, rdseed, adx, smap, avx512ifma, clflushopt, clwb, avx512cd, sha_ni, avx512bw, avx512vl, xsaveopt, xsavec, xgetbv1, xsaves, user_shstk, avx_vnni, avx512_bf16, vnmi, avx512vbmi, umip, waitpkg, avx512_vbmi2, gfni, vaes, vpclmulqdq, avx512_vnni, avx512_bitalg, avx512_vpopcntdq, la57, rdpid, cldemote, movdiri, movdir64b, fsrm, serialize, tsxldtrk, ibt, amx_bf16, avx512_fp16, amx_tile, amx_int8, arch_capabilities
Ecpus
24.6
Scalability
51.25

System Resources and Accelerators

MEMORY
Memory Amount
2 TB
Memory Amount Actual
2 TB
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

      A high-frequency, memory-intensive virtual server featuring massive RAM capacity and advanced matrix extensions for demanding enterprise database workloads.

      Memory OptimizedCompute Optimized

      Microsoft Azure FX96-48ms_v2 is a memory-optimized virtual machine powered by a dedicated 4.2 GHz Intel Xeon 8573C processor. Operating on the Microsoft Hyper-V hypervisor, it features 48 vCPUs, 24 physical cores, and a substantial 1832.0 GB of RAM, providing 38.17 GB of memory per core. The processor includes a 260 MB L3 cache and supports advanced instruction sets like AVX-512 and Intel AMX. While it lacks local storage and dedicated GPUs, it is premium storage capable. Benchmarks highlight top-tier single-core performance and strong memory bandwidth, with uncached large-block reads reaching 332.13 GB/sec and Redis SET operations at 74.96 million operations per second. This server is optimized for memory-intensive databases, large-scale in-memory data processing, and enterprise workloads requiring high single-core compute speeds.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      3.8Score
      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) 10,004,507 ops/sec 1,919,289 ops/sec 5.3 50.00% 50.00% +130.00%
      Redis RPS (pipeline=16, SET) 53,961,862 ops/sec 11,728,058 ops/sec 4.5 20.00% 20.00% +35.00%
      PassMark Memory Mark (composite) 2,655 2,416 1.1 10.00% 10.00% +0.96%
      Memory bandwidth (read, 16 MB ~ L3) 535,514 MB/sec 108,466 MB/sec 4.9 10.00% 10.00% +17.00%
      PassMark single-thread CPU 3,246 Mops/s 2,365 Mops/s 1.3 10.00% 10.00% +2.70%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 2,341

      Geekbench Multi-Core

      Score: 20,535

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 70,705
      Compression
      		 915,930
      Encryption
      		 56,174
      Extended Instructions
      		 75,439
      Floating Point Maths
      		 180,786
      Integer Maths
      		 255,174
      Physics
      		 11,782
      Prime Numbers
      		 511
      Single Threaded
      		 3,246
      String Sorting
      		 126,176

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2,655
      Database Operations
      		 28,806
      Memory Latency
      		 59
      Memory Read Cached
      		 29,145
      Memory Read Uncached
      		 10,167
      Memory Write
      		 9,418

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 217.22 196.22 0.90×
      bitops
      		 166,598 4,802,350 28.83×
      branch
      		 156,716 5,775,479 36.85×
      funccall
      		 846.91 26,284 31.03×
      funcret
      		 13,894 525,053 37.79×
      hash
      		 198,905 6,935,984 34.87×
      intmath
      		 73,395 2,109,141 28.74×
      nop
      		 296,555 5,708,482 19.25×
      prime
      		 530,226 15,356,413 28.96×
      rotate
      		 111,548 2,849,917 25.55×
      str
      		 956,886 36,475,269 38.12×
      wcs
      		 765,876 23,307,315 30.43×
      CryptographySingleMultiScaling
      crypt
      		 3,786 97,878 25.85×
      CompressionSingleMultiScaling
      jpeg
      		 949.48 29,668 31.25×
      zlib
      		 71.45 2,590 36.25×
      HypervisorSingleMultiScaling
      clock
      		 35,625 189,395 5.32×
      clone
      		 1,422 23,916 16.82×
      context
      		 5,948 234,588 39.44×
      cpu-sched
      		 64.49 2,994 46.42×
      eventfd
      		 35,958 1,727,747 48.05×
      fault
      		 28,080 201,004 7.16×
      fork
      		 6,407 55,582 8.68×
      getrandom
      		 65,872 2,342,605 35.56×
      hrtimers
      		 131,637 5,532,129 42.03×
      mprotect
      		 560,802 15,699,647 27.99×
      mtx
      		 12,699,429 1,431,092,636 112.69×
      munmap
      		 4,852 55,102 11.36×
      null
      		 977,153 36,808,106 37.67×
      pipe
      		 723,156 33,904,490 46.88×
      priv-instr
      		 959,636 16,999,774 17.71×
      resched
      		 10,031,873 4,092,335 0.41×
      switch
      		 44,722 16,700,624 373.44×
      timermix
      		 289,267 10,392,170 35.93×
      tlb-shootdown
      		 6,770 92,592 13.68×
      tsc
      		 1,020,934 37,267,427 36.50×
      usersyscall
      		 816,838 16,404,048 20.08×
      vdso
      		 119,442,078 4,212,714,532 35.27×
      vfork
      		 28,740 167,096 5.81×
      x86syscall
      		 11,731,062 474,729,230 40.47×
      yield
      		 74,080,783 69,237,787 0.93×
      zero
      		 6,521,902 258,304,486 39.61×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 18,108 564,289 31.16×
      expmath
      		 3,950 137,362 34.77×
      fma
      		 1,465,053 45,006,626 30.72×
      fp
      		 244.18 8,174 33.48×
      fractal
      		 7.2 251.86 34.98×
      hyperbolic
      		 4,541 157,466 34.67×
      logmath
      		 5,826 221,362 38.00×
      matrix
      		 5,708 178,475 31.27×
      matrix-3d
      		 762.74 14,879 19.51×
      monte-carlo
      		 334.18 12,968 38.81×
      mpfr
      		 1,966 52,910 26.92×
      powmath
      		 2,203 80,177 36.40×
      trig
      		 2,995 95,120 31.76×
      veccmp
      		 28,010 781,614 27.90×
      vecfp
      		 1,733 52,618 30.37×
      vecmath
      		 4,394 148,170 33.72×
      vecshuf
      		 925.74 25,401 27.44×
      vecwide
      		 40,190 1,179,077 29.34×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 10 288.79 28.88×
      bsearch
      		 322.69 10,837 33.58×
      bubblesort
      		 1.2 38.4 32.00×
      fibsearch
      		 345.17 9,997 28.96×
      heapsort
      		 11.2 373.59 33.36×
      hsearch
      		 9,212 278,726 30.26×
      insertionsort
      		 14.4 303.6 21.08×
      malloc
      		 3,172,932 50,189,557 15.82×
      mcontend
      		 60.01 8,327 138.76×
      mergesort
      		 34.4 1,178 34.23×
      qsort
      		 24.6 827.38 33.63×
      skiplist
      		 6,117 231,331 37.82×
      tree
      		 2 66.99 33.49×
      MemorySingleMultiScaling
      cache
      		 237,184 5,082,461 21.43×
      cachehammer
      		 224,013 5,627,410 25.12×
      cacheline
      		 40.76 3,572 87.64×
      l1cache
      		 1,236 11,088 8.97×
      memcpy
      		 498.66 11,969 24.00×
      memrate
      		 0.13 5.71 43.92×
      memthrash
      		 127.54 1,265 9.92×
      ptr-chase
      		 35,645,219 788,481,705 22.12×
      spinmem
      		 429.39 2,026 4.72×
      stream
      		 3.4 3,090 908.96×
      vm
      		 205,208 300,038 1.46×

      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
      FX2ms_v2 242 GiB0
      FX4-2ms_v2 284 GiB0
      FX8-2ms_v2 2168 GiB0
      FX4ms_v2 484 GiB0
      FX8-4ms_v2 4168 GiB0
      FX16-4ms_v2 4336 GiB0
      FX12-6ms_v2 6252 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      FX96-48ms_v2 FAQs