GPU-64xCPU-320GB-4xRTXPRO6000 by UpCloud

GPU-64xCPU-320GB-4xRTXPRO6000 is a GPU (64 vCPUs, 320 GiB RAM, 4x RTXPRO6000) server offered by UpCloud with 64 vCPUs, 320 GiB of memory and 0 GB of storage. The pricing starts at 3.8879 USD per hour.
64 vCPU
320 GiB Memory
4 GPU
Spare SCore
236,276
(All-cores)
3,717
(Single-core)

Specifications

Server Metadata

Vendor ID
upcloud
Name
GPU-64xCPU-320GB-4xRTXPRO6000
Description
GPU (64 vCPUs, 320 GiB RAM, 4x RTXPRO6000)
Family
GPU
Hw Virt
Average Time To Start
61.5
Status
active
Observed At
2026-10-31T22:48:31.123086

Availability

REGION / IDSPOTONDEMAND
Helsinki #2 (FI) / fi-hel2
3.8879 USD/h 7.3732 USD/h

Processor

vCPUs
64
Hypervisor
KVM
CPU Allocation
Shared
CPU Cores
64
CPU Speed
2 GHz
CPU Architecture
x86_64
CPU Manufacturer
AMD
CPU Family
EPYC
CPU Model
9555
CPU L1D Cache
64 KiB
CPU L1D Cache Total
4 MiB
CPU L1I Cache
64 KiB
CPU L1I Cache Total
4 MiB
CPU L2 Cache
512 KiB
CPU L2 Cache Total
32 MiB
CPU L3 Cache
16 MiB
CPU L3 Cache Total
16 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, tsc_known_freq, pni, pclmulqdq, ssse3, fma, cx16, pcid, sse4_1, sse4_2, x2apic, movbe, popcnt, tsc_deadline_timer, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, cmp_legacy, cr8_legacy, abm, sse4a, misalignsse, 3dnowprefetch, osvw, perfctr_core, ssbd, ibrs, ibpb, stibp, vmmcall, fsgsbase, tsc_adjust, bmi1, avx2, smep, bmi2, erms, invpcid, avx512f, avx512dq, rdseed, adx, smap, avx512ifma, clflushopt, clwb, avx512cd, sha_ni, avx512bw, avx512vl, xsaveopt, xsavec, xgetbv1, xsaves, avx_vnni, avx512_bf16, clzero, xsaveerptr, wbnoinvd, arat, avx512vbmi, umip, pku, ospke, avx512_vbmi2, gfni, vaes, vpclmulqdq, avx512_vnni, avx512_bitalg, avx512_vpopcntdq, la57, rdpid, movdiri, movdir64b, fsrm, avx512_vp2intersect, arch_capabilities
Ecpus
63.6
Scalability
99.38

System Resources and Accelerators

MEMORY
Memory Amount
320 GiB
Memory Amount Actual
320 GiB
ACCELERATORS
Accelerator Count
4
Accelerator Memory Min
96 GiB
Accelerator Memory Total
384 GiB
Accelerator Type
GPU
Accelerator Manufacturer
NVIDIA
Accelerator Family
Blackwell
Accelerator Model
RTX PRO 6000
Accelerators
  • NVIDIA Blackwell NVIDIA RTX PRO 6000 Blackwell Server Edition (Memory amount: 97887, Firmware version: 595.91.07, BIOS version: 98.02.8D.00.01, Clock rate: 2430)
  • NVIDIA Blackwell NVIDIA RTX PRO 6000 Blackwell Server Edition (Memory amount: 97887, Firmware version: 595.91.07, BIOS version: 98.02.8D.00.01, Clock rate: 2430)
  • NVIDIA Blackwell NVIDIA RTX PRO 6000 Blackwell Server Edition (Memory amount: 97887, Firmware version: 595.91.07, BIOS version: 98.02.8D.00.01, Clock rate: 2430)
  • NVIDIA Blackwell NVIDIA RTX PRO 6000 Blackwell Server Edition (Memory amount: 97887, Firmware version: 595.91.07, BIOS version: 98.02.8D.00.01, Clock rate: 2430)
STORAGE
Storage Size
0 GB
Storages
    NETWORK
    Inbound Traffic
    0 GB/month
    Outbound Traffic
    51200 GB/month
    IPv4
    1

    CPU and System Topology

    Server Description

    A high-density GPU server featuring four advanced accelerators and sixty-four cores for demanding machine learning and parallel computing workloads.

    GPU AcceleratedGeneral Purpose

    UpCloud GPU-64xCPU-320GB-4xRTXPRO6000 is a high-density GPU-accelerated server featuring 64 AMD EPYC 9555 vCPUs, 320.0 GB of system memory, and four NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs with 382 GB of total VRAM. Built on the x86_64 architecture and managed via KVM virtualization, this server does not include local storage. It delivers top-tier benchmark performance, including 236275.73 in multi-core stress-ng tests and 7887.2 tokens per second for medium 7B LLM prompt processing. The system is highly optimized for parallel computing, machine learning inference, and data science workloads.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    11Score
    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.Partial coverage: missing component benchmark(s): PassMark Memory Mark (composite), PassMark single-thread CPU.
    Component Score Weight Impact
    Raw Reference Normalized Target Actual
    Redis RPS (pipeline=1, SET) 20,773,501 ops/sec 1,918,343 ops/sec 11 50.00% 62.00% +340.00%
    Redis RPS (pipeline=16, SET) 136,842,955 ops/sec 11,704,734 ops/sec 12 20.00% 25.00% +86.00%
    PassMark Memory Mark (composite) — 2,416 — 10.00% 0.00% —
    Memory bandwidth (read, 16 MB ~ L3) 915,180 MB/sec 108,466 MB/sec 8.4 10.00% 13.00% +32.00%
    PassMark single-thread CPU — 2,365 Mops/s — 10.00% 0.00% —

    GPU Bandwidth and Latency

    Node (all GPUs)
    Node baseline directional bandwidth
    		178.6 GB/s
    Node GPU-to-host bandwidth
    		216.5 GB/s
    Node host-to-GPU bandwidth
    		228.8 GB/s
    Single GPU slot
    Per-GPU GPU-to-host bandwidth
    		56.6 GB/s
    Per-GPU host-to-GPU bandwidth
    		57.9 GB/s
    Per-GPU host-device latency
    		639 ns
    Per-GPU device memory copy bandwidth
    		729.9 GB/s
    Benchmark Environment
    Driver Version
    		 595.91.07
    CUDA Version (driver)
    		 13.2
    nvbandwidth Version
    		 v0.8
    GPU Count
    		 4
    P2P Supported
    No
    Efficiency
    SM/CE copy efficiency
    		0.93

    Memory Bandwidth

    Compression

    OpenSSL

    Stress-ng Stressors

    CPU integerSingleMultiScaling
    atomic
    		 491.73 353.35 0.72×
    bitops
    		 227,449 14,443,907 63.50×
    branch
    		 181,767 11,260,326 61.95×
    funccall
    		 894.51 56,726 63.42×
    funcret
    		 26,437 1,681,993 63.62×
    hash
    		 214,352 13,661,284 63.73×
    intmath
    		 78,370 4,986,524 63.63×
    nop
    		 423,952 26,947,694 63.56×
    prime
    		 607,791 38,663,378 63.61×
    rotate
    		 140,693 8,932,650 63.49×
    str
    		 1,586,272 94,304,431 59.45×
    wcs
    		 1,055,754 65,379,998 61.93×
    CryptographySingleMultiScaling
    crypt
    		 5,284 339,551 64.27×
    CompressionSingleMultiScaling
    jpeg
    		 1,237 65,274 52.78×
    zlib
    		 81.58 4,536 55.60×
    HypervisorSingleMultiScaling
    clock
    		 69,170 170,183 2.46×
    clone
    		 317.53 14,840 46.74×
    context
    		 8,491 536,619 63.20×
    cpu-sched
    		 73.96 4,060 54.89×
    eventfd
    		 72,872 1,805,381 24.77×
    fault
    		 38,772 122,288 3.15×
    fork
    		 4,417 46,732 10.58×
    getrandom
    		 96,943 6,171,418 63.66×
    hrtimers
    		 200,716 5,245,495 26.13×
    mprotect
    		 485,787 17,989,234 37.03×
    mtx
    		 37,519,364 5,399,635,895 143.92×
    munmap
    		 3,429 46,353 13.52×
    null
    		 1,409,305 89,162,239 63.27×
    pipe
    		 685,708 28,575,773 41.67×
    priv-instr
    		 1,373,426 16,078,678 11.71×
    resched
    		 7,645,138 20,034,831 2.62×
    switch
    		 118,201 2,570,658 21.75×
    timermix
    		 341,103 17,663,141 51.78×
    tlb-shootdown
    		 15,143 345,332 22.80×
    tsc
    		 872,419 55,490,867 63.61×
    usersyscall
    		 1,038,258 15,868,615 15.28×
    vdso
    		 96,285,459 6,123,375,705 63.60×
    vfork
    		 26,776 116,451 4.35×
    x86syscall
    		 18,449,869 1,171,495,481 63.50×
    yield
    		 80,357,353 100,311,270 1.25×
    zero
    		 10,891,463 682,650,484 62.68×
    CPU float/SIMDSingleMultiScaling
    eigen
    		 17,242 1,098,847 63.73×
    expmath
    		 3,952 251,482 63.64×
    fma
    		 1,542,430 97,932,255 63.49×
    fp
    		 209.74 13,000 61.98×
    fractal
    		 8.8 550.39 62.54×
    hyperbolic
    		 5,385 342,795 63.66×
    logmath
    		 5,614 356,943 63.58×
    matrix
    		 9,185 545,876 59.43×
    matrix-3d
    		 1,376 24,547 17.84×
    monte-carlo
    		 452.42 28,481 62.95×
    mpfr
    		 2,376 150,648 63.41×
    powmath
    		 1,822 115,682 63.49×
    trig
    		 2,406 153,097 63.64×
    veccmp
    		 29,779 1,884,939 63.30×
    vecfp
    		 2,307 149,735 64.89×
    vecmath
    		 4,680 298,037 63.68×
    vecshuf
    		 989.31 62,751 63.43×
    vecwide
    		 39,751 2,510,739 63.16×
    AlgorithmsSingleMultiScaling
    bitonicsort
    		 12.8 805.58 62.94×
    bsearch
    		 361.72 22,526 62.27×
    bubblesort
    		 1.2 76.8 64.00×
    fibsearch
    		 419.13 26,886 64.15×
    heapsort
    		 14.2 894.38 62.98×
    hsearch
    		 13,144 828,006 63.00×
    insertionsort
    		 15 868.8 57.92×
    malloc
    		 4,986,136 99,881,075 20.03×
    mcontend
    		 68.48 8,389 122.50×
    mergesort
    		 38.6 2,437 63.13×
    qsort
    		 26.4 1,642 62.21×
    skiplist
    		 8,390 527,100 62.83×
    tree
    		 2.6 147.95 56.90×
    MemorySingleMultiScaling
    cache
    		 1,072,947 1,162,698 1.08×
    cachehammer
    		 224,522 9,112,131 40.58×
    cacheline
    		 55.37 3,640 65.74×
    l1cache
    		 671.04 40,879 60.92×
    memcpy
    		 805.53 50,816 63.08×
    memrate
    		 0.74 27.41 37.04×
    memthrash
    		 196.45 2,475 12.60×
    ptr-chase
    		 76,471,549 1,035,526,302 13.54×
    spinmem
    		 324.79 5,817 17.91×
    stream
    		 402.52 182,489 453.37×
    vm
    		 234,313 298,413 1.27×

    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
    GPU-8xCPU-64GB-1xL4 864 GiB1
    GPU-8xCPU-64GB-1xL40S 864 GiB1
    GPU-12xCPU-128GB-1xL4 12128 GiB1
    GPU-12xCPU-128GB-1xL40S 12128 GiB1
    GPU-12xCPU-128GB-2xL4 12128 GiB2
    GPU-12xCPU-128GB-2xL40S 12128 GiB2
    GPU-16xCPU-80GB-1xRTXPRO6000 1680 GiB1

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYAccelerators

    GPU-64xCPU-320GB-4xRTXPRO6000 FAQs