b3-512 by OVHcloud

b3-512 is a General Purpose (128 vCPUs, 512 GiB RAM, 400 GB NVMe) server offered by OVHcloud with 128 vCPUs, 512 GiB of memory and 400 GB of storage. The pricing starts at 3.6449 USD per hour.
128 vCPU
512 GiB Memory
400 GB Storage
Spare SCore
287,994
(All-cores)
3,078
(Single-core)

Specifications

Server Metadata

Vendor ID
ovh
Name
b3-512
Description
General Purpose (128 vCPUs, 512 GiB RAM, 400 GB NVMe)
Family
General Purpose
Hw Virt
Average Time To Start
61
Status
active
Observed At
2026-10-29T00:03:07.907554

Availability

REGION / IDSPOTONDEMAND
AP-SOUTHEAST-SYD-2 (AU) / AP-SOUTHEAST-SYD-2
- 3.6449 USD/h
AP-SOUTH-MUM-1 (IN) / AP-SOUTH-MUM-1
- 3.6449 USD/h
BHS5 (CA) / BHS5
- 3.6449 USD/h
DE1 (DE) / DE1
- 3.6449 USD/h
EU-SOUTH-MIL (IT) / EU-SOUTH-MIL
- 3.6449 USD/h
EU-WEST-PAR (FR) / EU-WEST-PAR
- 3.6449 USD/h
GRA11 (FR) / GRA11
- 3.6449 USD/h
GRA7 (FR) / GRA7
- 3.6449 USD/h
GRA9 (FR) / GRA9
- 3.6449 USD/h
RBX-A (FR) / RBX-A
- 3.6449 USD/h
SBG5 (FR) / SBG5
- 3.6449 USD/h
SBG7 (FR) / SBG7
- 3.6449 USD/h
SGP1 (SG) / SGP1
- 3.6449 USD/h
SYD1 (AU) / SYD1
- 3.6449 USD/h
UK1 (GB) / UK1
- 3.6449 USD/h
WAW1 (PL) / WAW1
- 3.6449 USD/h

Processor

vCPUs
128
Hypervisor
KVM
CPU Allocation
Dedicated
CPU Cores
128
CPU Speed
2.3 GHz
CPU Architecture
x86_64
CPU Manufacturer
AMD
CPU Family
EPYC
CPU L1D Cache
32 KiB
CPU L1D Cache Total
4 MiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
4 MiB
CPU L2 Cache
512 KiB
CPU L2 Cache Total
64 MiB
CPU L3 Cache
32 MiB
CPU L3 Cache Total
4 GiB
CPU Flags
fpu, vme, de, pse, tsc, msr, pae, mce, cx8, apic, sep, mtrr, pge, mca, cmov, pat, pse36, clflush, mmx, fxsr, sse, sse2, syscall, nx, mmxext, fxsr_opt, pdpe1gb, rdtscp, lm, rep_good, nopl, cpuid, extd_apicid, tsc_known_freq, pni, pclmulqdq, ssse3, fma, cx16, pcid, sse4_1, sse4_2, x2apic, movbe, popcnt, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, svm, cr8_legacy, abm, sse4a, misalignsse, 3dnowprefetch, osvw, topoext, perfctr_core, ssbd, ibrs, ibpb, stibp, vmmcall, fsgsbase, bmi1, avx2, smep, bmi2, erms, invpcid, rdseed, adx, smap, clflushopt, clwb, sha_ni, xsaveopt, xsavec, xgetbv1, xsaves, clzero, xsaveerptr, wbnoinvd, arat, npt, nrip_save, umip, pku, ospke, rdpid, fsrm
Ecpus
93.6
Scalability
73.12

System Resources and Accelerators

MEMORY
Memory Amount
512 GiB
Memory Amount Actual
500 GiB
ACCELERATORS
Accelerator Count
0
Accelerator Memory Min
0 MiB
Accelerator Memory Total
0 MiB
Accelerators
    STORAGE
    Storage Size
    400 GB
    Storage Type
    nvme ssd
    Storages
    • 400 GB nvme ssd
    NETWORK
    Network Speed Baseline
    20 Gbps
    Network Speed Max
    20 Gbps
    Inbound Traffic
    0 GB/month
    Outbound Traffic
    0 GB/month
    IPv4
    1

    CPU and System Topology

    Server Description

    A high-density, 128-core dedicated processor platform with balanced memory and NVMe storage for highly parallelized enterprise workloads.

    General PurposeCompute OptimizedStorage & Database

    OVHcloud b3-512 is a General Purpose server featuring 128 dedicated AMD EPYC physical cores and 128 vCPUs running at 2.3 GHz on a KVM hypervisor. It is equipped with 512.0 GB of RAM, a 400 GB NVMe SSD, and 20 Gbps baseline network bandwidth. The server delivers top-tier multi-core CPU and memory performance, ranking in the top 10% for multi-threaded benchmarks, software compilation, and Redis operations. However, single-threaded performance and large-model LLM text generation are more limited, with the latter falling into the bottom 10% tier. This configuration offers high resource density for parallel processing, database operations, and multi-threaded workloads.

    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) 9,815,093 ops/sec 1,919,289 ops/sec 5.2 50.00% 50.00% +130.00%
    Redis RPS (pipeline=16, SET) 94,019,546 ops/sec 11,728,058 ops/sec 7.8 20.00% 20.00% +51.00%
    PassMark Memory Mark (composite) 3,004 2,416 1.2 10.00% 10.00% +1.80%
    Memory bandwidth (read, 16 MB ~ L3) 208,285 MB/sec 108,466 MB/sec 1.9 10.00% 10.00% +6.60%
    PassMark single-thread CPU 2,936 Mops/s 2,365 Mops/s 1.2 10.00% 10.00% +1.80%

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 1,891

    Geekbench Multi-Core

    Score: 20,790

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 113,811
    Compression
    		 2,214,922
    Encryption
    		 139,192
    Extended Instructions
    		 151,387
    Floating Point Maths
    		 451,092
    Integer Maths
    		 674,319
    Physics
    		 19,795
    Prime Numbers
    		 1,485
    Single Threaded
    		 2,936
    String Sorting
    		 316,816

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 3,004
    Database Operations
    		 29,393
    Memory Latency
    		 71
    Memory Read Cached
    		 27,855
    Memory Read Uncached
    		 26,643
    Memory Write
    		 25,812

    Stress-ng Stressors

    CPU integerSingleMultiScaling
    atomic
    		 853.27 253.56 0.30×
    bitops
    		 160,772 13,717,020 85.32×
    branch
    		 213,196 18,294,037 85.81×
    funccall
    		 609.45 54,728 89.80×
    funcret
    		 21,366 1,771,645 82.92×
    hash
    		 163,372 16,135,997 98.77×
    intmath
    		 66,487 6,778,542 101.95×
    nop
    		 627,435 58,475,826 93.20×
    prime
    		 495,115 40,091,646 80.97×
    rotate
    		 88,313 7,933,629 89.84×
    str
    		 1,080,429 79,029,265 73.15×
    wcs
    		 693,059 47,472,837 68.50×
    CryptographySingleMultiScaling
    crypt
    		 3,738 284,234 76.04×
    CompressionSingleMultiScaling
    jpeg
    		 897.66 52,213 58.17×
    zlib
    		 73.75 5,962 80.84×
    HypervisorSingleMultiScaling
    clock
    		 17,283 200,139 11.58×
    clone
    		 241.25 8,739 36.22×
    context
    		 2,938 322,142 109.63×
    cpu-sched
    		 61.26 8,110 132.39×
    eventfd
    		 36,606 2,820,463 77.05×
    fault
    		 10,559 139,430 13.21×
    fork
    		 2,927 70,728 24.16×
    getrandom
    		 53,124 4,487,401 84.47×
    hrtimers
    		 277,392 7,300,914 26.32×
    mprotect
    		 615,749 19,017,035 30.88×
    mtx
    		 56,740,800 7,395,103,521 130.33×
    munmap
    		 2,223 78,871 35.48×
    null
    		 354,520 37,155,133 104.80×
    pipe
    		 360,949 25,714,228 71.24×
    priv-instr
    		 420,581 17,088,892 40.63×
    resched
    		 6,758,246 16,425,029 2.43×
    switch
    		 82,275 6,912,631 84.02×
    timermix
    		 166,109 15,443,426 92.97×
    tlb-shootdown
    		 14,892 234,221 15.73×
    tsc
    		 782,537 96,434,566 123.23×
    usersyscall
    		 324,413 16,037,816 49.44×
    vdso
    		 83,928,888 8,535,547,012 101.70×
    vfork
    		 18,896 107,798 5.70×
    x86syscall
    		 3,990,364 428,610,600 107.41×
    yield
    		 66,804,591 85,637,075 1.28×
    zero
    		 2,757,222 281,448,499 102.08×
    CPU float/SIMDSingleMultiScaling
    eigen
    		 16,596 1,322,259 79.67×
    expmath
    		 2,420 240,278 99.30×
    fma
    		 920,026 81,014,574 88.06×
    fp
    		 251.98 23,771 94.34×
    fractal
    		 7.4 649.66 87.79×
    hyperbolic
    		 3,615 356,937 98.75×
    logmath
    		 4,560 408,749 89.65×
    matrix
    		 4,903 352,625 71.91×
    matrix-3d
    		 432.28 10,454 24.18×
    monte-carlo
    		 171.45 16,554 96.55×
    mpfr
    		 1,701 137,561 80.87×
    powmath
    		 1,296 128,736 99.35×
    trig
    		 1,873 165,038 88.12×
    veccmp
    		 19,046 1,519,449 79.78×
    vecfp
    		 1,813 152,097 83.88×
    vecmath
    		 4,023 379,571 94.36×
    vecshuf
    		 638.11 54,630 85.61×
    vecwide
    		 28,641 2,046,448 71.45×
    AlgorithmsSingleMultiScaling
    bitonicsort
    		 10.4 829.58 79.77×
    bsearch
    		 306.54 24,991 81.53×
    bubblesort
    		 0.8 65.4 81.75×
    fibsearch
    		 379.24 33,716 88.90×
    heapsort
    		 11 906.77 82.43×
    hsearch
    		 11,423 837,860 73.35×
    insertionsort
    		 13.2 858.19 65.01×
    malloc
    		 3,757,483 189,074,163 50.32×
    mcontend
    		 79.52 19,372 243.61×
    mergesort
    		 33.8 2,785 82.39×
    qsort
    		 22.2 1,734 78.10×
    skiplist
    		 7,047 641,602 91.05×
    tree
    		 2 129.07 64.53×
    MemorySingleMultiScaling
    cache
    		 740,663 1,553,784 2.10×
    cachehammer
    		 287,971 18,693,052 64.91×
    cacheline
    		 55.76 4,519 81.04×
    l1cache
    		 354.74 21,559 60.77×
    memcpy
    		 445.86 34,044 76.36×
    memrate
    		 3.72 31.94 8.59×
    memthrash
    		 354.52 517.22 1.46×
    ptr-chase
    		 40,395,619 1,051,145,662 26.02×
    spinmem
    		 221.99 6,100 27.48×
    stream
    		 128.47 151,831 1181.84×
    vm
    		 100,861 309,472 3.07×

    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

    PostgreSQL heavy read-only throughput

    Alternatives

    Servers of the Same Family

    INSTANCEvCPUsMEMORYAccelerators
    b2-7 27 GiB0
    b3-8 28 GiB0
    b2-15 415 GiB0
    b3-16 416 GiB0
    b2-30 830 GiB0
    b3-32 832 GiB0
    b2-60 1660 GiB0

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYAccelerators

    b3-512 FAQs