F64s_v2 by Microsoft Azure

F64s_v2 is a FSv2 family [Premium Storage capable] [Intel processor] 64 vCPUs server offered by Microsoft Azure with 64 vCPUs, 128 GiB of memory and 524 GB of storage. The pricing starts at 0.3552 USD per hour.
64 vCPU
128 GiB Memory
524 GB Storage
Spare SCore
59,598
(All-cores)
1,457
(Single-core)

Specifications

Server Metadata

Vendor ID
azure
Server ID
Standard_F64s_v2
Name
F64s_v2
API Reference
Standard_F64s_v2
Description
FSv2 family [Premium Storage capable] [Intel processor] 64 vCPUs
Family
FSv2
Hw Virt
Average Time To Start
37
Status
planned-for-retirement
Observed At
2026-10-24T01:15:01.836961

Availability

REGION / IDSPOTONDEMAND
West US 2 (US) / westus2
0.5001 USD/h 2.706 USD/h
West US 3 (US) / westus3
0.5001 USD/h 2.706 USD/h
East US (US) / eastus
0.5953 USD/h 2.706 USD/h
East US 2 (US) / eastus2
1.0762 USD/h 2.706 USD/h
Central India (IN) / centralindia
0.5027 USD/h 2.72 USD/h
North Central US (US) / northcentralus
0.5027 USD/h 2.72 USD/h
West India (IN) / westindia
0.5027 USD/h 2.72 USD/h
South Africa West (ZA) / southafricawest
0.5043 USD/h 2.72 USD/h
Jio India Central (IN) / jioindiacentral
- 2.72 USD/h
Jio India West (IN) / jioindiawest
- 2.72 USD/h
Indonesia Central (ID) / indonesiacentral
0.5215 USD/h 2.822 USD/h
Malaysia West (MY) / malaysiawest
0.5215 USD/h 2.822 USD/h
Canada East (CA) / canadaeast
0.5479 USD/h 2.965 USD/h
Canada Central (CA) / canadacentral
0.9921 USD/h 2.965 USD/h
Mexico Central (ZA) / mexicocentral
0.5503 USD/h 2.978 USD/h
South India (IN) / southindia
0.5529 USD/h 2.992 USD/h
Korea Central (KR) / koreacentral
0.5677 USD/h 3.072 USD/h
Spain Central (ES) / spaincentral
0.5677 USD/h 3.072 USD/h
North Europe (IE) / northeurope
0.6832 USD/h 3.072 USD/h
Korea South (KR) / koreasouth
0.5681 USD/h 3.074 USD/h
Austria East (AT) / austriaeast
0.5736 USD/h 3.104 USD/h
Belgium Central (BE) / belgiumcentral
0.5736 USD/h 3.104 USD/h
Germany West Central (DE) / germanywestcentral
0.5736 USD/h 3.104 USD/h
Poland Central (PL) / polandcentral
0.5736 USD/h 3.104 USD/h
Sweden Central (SE) / swedencentral
0.5736 USD/h 3.104 USD/h
West Europe (NL) / westeurope
0.5736 USD/h 3.104 USD/h
Italy North (IT) / italynorth
0.5755 USD/h 3.104 USD/h
Southeast Asia (SG) / southeastasia
0.5795 USD/h 3.136 USD/h
UK South (GB) / uksouth
0.5947 USD/h 3.232 USD/h
France Central (FR) / francecentral
0.5973 USD/h 3.232 USD/h
Israel Central (IL) / israelcentral
0.5973 USD/h 3.232 USD/h
UK West (GB) / ukwest
0.5982 USD/h 3.237 USD/h
Central US (US) / centralus
0.5872 USD/h 3.264 USD/h
South Central US (US) / southcentralus
0.6032 USD/h 3.264 USD/h
West Central US (US) / westcentralus
0.6032 USD/h 3.264 USD/h
Qatar Central (QA) / qatarcentral
0.6239 USD/h 3.376 USD/h
UAE North (AE) / uaenorth
0.6246 USD/h 3.38 USD/h
West US (US) / westus
0.6268 USD/h 3.392 USD/h
Switzerland North (CH) / switzerlandnorth
0.631 USD/h 3.4144 USD/h
Norway East (NO) / norwayeast
0.6316 USD/h 3.418 USD/h
Japan East (JP) / japaneast
0.6328 USD/h 3.424 USD/h
East Asia (HK) / eastasia
0.6387 USD/h 3.456 USD/h
Australia Central 2 (AU) / australiacentral2
0.3552 USD/h 3.552 USD/h
Australia Central (AU) / australiacentral
0.6564 USD/h 3.552 USD/h
Australia East (AU) / australiaeast
0.6564 USD/h 3.552 USD/h
Australia Southeast (AU) / australiasoutheast
0.6584 USD/h 3.563 USD/h
South Africa North (ZA) / southafricanorth
0.6736 USD/h 3.645 USD/h
New Zealand North (NZ) / newzealandnorth
0.6895 USD/h 3.731 USD/h
Japan West (JP) / japanwest
0.696 USD/h 3.754 USD/h
Chile Central (CL) / chilecentral
0.7004 USD/h 3.79 USD/h
Germany North (DE) / germanynorth
0.7457 USD/h 4.035 USD/h
UAE Central (AE) / uaecentral
0.7457 USD/h 4.035 USD/h
France South (FR) / francesouth
0.7741 USD/h 4.189 USD/h
Brazil South (BR) / brazilsouth
0.7747 USD/h 4.192 USD/h
Switzerland West (CH) / switzerlandwest
0.8202 USD/h 4.4383 USD/h
Norway West (NO) / norwaywest
0.9345 USD/h 5.057 USD/h
Brazil Southeast (US) / brazilsoutheast
1.0072 USD/h 5.45 USD/h

Processor

vCPUs
64
Hypervisor
Microsoft Hyper-V
CPU Allocation
Dedicated
CPU Cores
32
CPU Speed
2.6 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU Model
8272CL
CPU L1D Cache
48 KiB
CPU L1D Cache Total
2 MiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
1 MiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
40 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, avx512f, avx512dq, rdseed, adx, smap, clflushopt, avx512cd, avx512bw, avx512vl, xsaveopt, xsavec, xsaves, vnmi, md_clear
Ecpus
40.9
Scalability
63.91

System Resources and Accelerators

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

    CPU and System Topology

    Server Description

    A compute-optimized virtual machine featuring sixty-four dedicated vCPUs and high memory bandwidth for intensive, CPU-bound processing workloads.

    Compute Optimized

    Microsoft Azure F64s_v2 is a compute-optimized virtual machine from the FSv2 family, utilizing an Intel Xeon 8272CL processor with x86_64 architecture. It delivers 64 dedicated vCPUs across 32 physical cores, 128 GB of RAM, and 524 GB of local storage. Operating on the Microsoft Hyper-V hypervisor, this instance lacks GPU acceleration but supports Premium Storage. Benchmark results show strong performance in large-block memory bandwidth, with read speeds of 208.5 GB/sec and write speeds of 91.43 GB/sec, alongside strong Passmark extended instruction capabilities. However, large LLM inference tasks perform poorly. This server is qualitatively cost-efficient for compute-heavy, memory-lean applications, making it suitable for batch processing, software compilation, web serving, and vector-heavy workloads.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    2.1Score
    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) 5,048,298 ops/sec 1,919,289 ops/sec 2.6 50.00% 50.00% +61.00%
    Redis RPS (pipeline=16, SET) 31,540,491 ops/sec 11,728,058 ops/sec 2.7 20.00% 20.00% +22.00%
    PassMark Memory Mark (composite) 2,406 2,416 1 10.00% 10.00% 0.00%
    Memory bandwidth (read, 16 MB ~ L3) 211,014 MB/sec 108,466 MB/sec 1.9 10.00% 10.00% +6.60%
    PassMark single-thread CPU 2,010 Mops/s 2,365 Mops/s 0.83 10.00% 10.00% -1.80%

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 1,202

    Geekbench Multi-Core

    Score: 12,145

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 45,171
    Compression
    		 858,425
    Encryption
    		 26,106
    Extended Instructions
    		 54,211
    Floating Point Maths
    		 106,383
    Integer Maths
    		 197,457
    Physics
    		 3,856
    Prime Numbers
    		 210
    Single Threaded
    		 2,010
    String Sorting
    		 95,030

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 2,406
    Database Operations
    		 20,714
    Memory Latency
    		 60
    Memory Read Cached
    		 24,263
    Memory Read Uncached
    		 9,868
    Memory Write
    		 8,129

    Stress-ng Stressors

    CPU integerSingleMultiScaling
    atomic
    		 224.21 210.81 0.94×
    bitops
    		 108,066 3,492,946 32.32×
    branch
    		 114,056 5,738,626 50.31×
    funccall
    		 527.38 17,033 32.30×
    funcret
    		 9,961 428,914 43.06×
    hash
    		 125,890 5,715,594 45.40×
    intmath
    		 50,573 1,960,111 38.76×
    nop
    		 155,566 4,346,706 27.94×
    prime
    		 330,610 11,389,744 34.45×
    rotate
    		 81,172 2,725,198 33.57×
    str
    		 717,499 24,558,722 34.23×
    wcs
    		 510,752 13,771,826 26.96×
    CryptographySingleMultiScaling
    crypt
    		 2,363 69,162 29.27×
    CompressionSingleMultiScaling
    jpeg
    		 592.23 23,206 39.18×
    zlib
    		 30.74 2,380 77.42×
    HypervisorSingleMultiScaling
    clock
    		 17,188 197,211 11.47×
    clone
    		 1,280 27,070 21.14×
    context
    		 1,726 67,144 38.90×
    cpu-sched
    		 67.82 4,046 59.65×
    eventfd
    		 36,186 1,273,915 35.21×
    fault
    		 11,268 234,146 20.78×
    fork
    		 4,133 54,749 13.25×
    getrandom
    		 39,931 1,455,408 36.45×
    hrtimers
    		 319,819 6,955,362 21.75×
    mprotect
    		 1,140,775 8,802,007 7.72×
    mtx
    		 13,946,256 1,182,166,316 84.77×
    munmap
    		 2,958 54,418 18.39×
    null
    		 186,175 6,658,583 35.77×
    pipe
    		 964,491 20,368,423 21.12×
    priv-instr
    		 399,568 10,355,130 25.92×
    resched
    		 7,601,193 3,607,900 0.47×
    switch
    		 70,219 10,621,344 151.26×
    timermix
    		 197,060 8,598,322 43.63×
    tlb-shootdown
    		 10,077 75,108 7.45×
    tsc
    		 744,163 32,432,821 43.58×
    usersyscall
    		 280,195 8,895,106 31.75×
    vdso
    		 76,386,285 2,792,079,809 36.55×
    vfork
    		 23,525 232,727 9.89×
    x86syscall
    		 2,108,178 72,766,441 34.52×
    yield
    		 28,304,146 32,674,396 1.15×
    zero
    		 1,589,949 58,500,315 36.79×
    CPU float/SIMDSingleMultiScaling
    eigen
    		 12,286 493,331 40.15×
    expmath
    		 2,402 111,300 46.34×
    fma
    		 563,595 30,989,848 54.99×
    fp
    		 166.4 5,413 32.53×
    fractal
    		 4.2 192.87 45.92×
    hyperbolic
    		 2,518 119,590 47.50×
    logmath
    		 4,021 184,314 45.84×
    matrix
    		 3,157 139,219 44.10×
    matrix-3d
    		 719.2 5,936 8.25×
    monte-carlo
    		 96.49 3,917 40.59×
    mpfr
    		 1,173 39,543 33.71×
    powmath
    		 1,403 66,079 47.11×
    trig
    		 1,637 65,746 40.16×
    veccmp
    		 17,254 516,232 29.92×
    vecfp
    		 1,269 49,198 38.78×
    vecmath
    		 2,724 122,956 45.14×
    vecshuf
    		 552.83 18,997 34.36×
    vecwide
    		 26,515 970,434 36.60×
    AlgorithmsSingleMultiScaling
    bitonicsort
    		 6.6 214.39 32.48×
    bsearch
    		 203.89 8,531 41.84×
    bubblesort
    		 0.8 12.8 16.00×
    fibsearch
    		 240.6 9,295 38.63×
    heapsort
    		 7.8 286.99 36.79×
    hsearch
    		 5,892 213,224 36.19×
    insertionsort
    		 8.6 163.2 18.98×
    malloc
    		 2,213,185 52,110,619 23.55×
    mcontend
    		 103.71 10,540 101.63×
    mergesort
    		 22.2 960.36 43.26×
    qsort
    		 17.2 566.18 32.92×
    skiplist
    		 4,520 209,029 46.25×
    tree
    		 1.4 36.39 25.99×
    MemorySingleMultiScaling
    cache
    		 349,602 971,664 2.78×
    cachehammer
    		 371,845 14,382,054 38.68×
    cacheline
    		 60.55 3,626 59.88×
    l1cache
    		 762.05 9,787 12.84×
    memcpy
    		 339.2 10,542 31.08×
    memrate
    		 1.57 24.03 15.31×
    memthrash
    		 243.82 1,261 5.17×
    ptr-chase
    		 35,637,468 564,096,975 15.83×
    spinmem
    		 374.58 1,465 3.91×
    stream
    		 39.29 23,675 602.58×
    vm
    		 89,353 302,827 3.39×

    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

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYAccelerators

    F64s_v2 FAQs