GPU-32xCPU-160GB-2xRTXPRO6000 by UpCloud

GPU-32xCPU-160GB-2xRTXPRO6000 is a GPU (32 vCPUs, 160 GiB RAM, 2x RTXPRO6000) server offered by UpCloud with 32 vCPUs, 160 GiB of memory and 0 GB of storage. The pricing starts at 1.9439 USD per hour.
32 vCPU
160 GiB Memory
2 GPU
Spare SCore
118,473
(All-cores)
3,719
(Single-core)

Specifications

Server Metadata

Vendor ID
upcloud
Name
GPU-32xCPU-160GB-2xRTXPRO6000
Description
GPU (32 vCPUs, 160 GiB RAM, 2x RTXPRO6000)
Family
GPU
Hw Virt
Average Time To Start
58
Status
active
Observed At
2026-10-31T22:48:31.121997

Availability

REGION / IDSPOTONDEMAND
Helsinki #2 (FI) / fi-hel2
1.9439 USD/h 3.6874 USD/h

Processor

vCPUs
32
Hypervisor
KVM
CPU Allocation
Shared
CPU Cores
32
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
2 MiB
CPU L1I Cache
64 KiB
CPU L1I Cache Total
2 MiB
CPU L2 Cache
512 KiB
CPU L2 Cache Total
16 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
31.9
Scalability
99.69

System Resources and Accelerators

MEMORY
Memory Amount
160 GiB
Memory Amount Actual
160 GiB
ACCELERATORS
Accelerator Count
2
Accelerator Memory Min
96 GiB
Accelerator Memory Total
192 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)
STORAGE
Storage Size
0 GB
Storages
    NETWORK
    Inbound Traffic
    0 GB/month
    Outbound Traffic
    40960 GB/month
    IPv4
    1

    CPU and System Topology

    Server Description

    A dual-GPU accelerated server featuring 191 GB VRAM and 32 AMD EPYC cores, optimized for high-throughput machine learning inference.

    GPU AcceleratedCompute Optimized

    UpCloud GPU-32xCPU-160GB-2xRTXPRO6000 is a KVM-based, GPU-accelerated server featuring an x86_64 AMD EPYC 9555 processor with 32 physical cores, 160.0 GB of RAM, and two NVIDIA RTX PRO 6000 Blackwell Server Edition GPUs providing 191 GB of total VRAM. Local storage is not included. The server delivers top-tier performance in LLM inference, achieving 8118.49 tokens/sec for prompt processing on a 7B model, alongside strong memory bandwidth of 455.64 GB/sec for large block reads. While the shared CPU allocation represents a potential tradeoff for sustained CPU-only workloads, the massive parallel processing power and VRAM capacity make this server highly cost-efficient for machine learning, ray tracing, and data science applications.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    4.8Score
    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) 11,191,453 ops/sec 1,918,343 ops/sec 5.8 50.00% 50.00% +140.00%
    Redis RPS (pipeline=16, SET) 74,718,198 ops/sec 11,704,734 ops/sec 6.2 20.00% 20.00% +44.00%
    PassMark Memory Mark (composite) 2,356 2,416 1 10.00% 10.00% 0.00%
    Memory bandwidth (read, 16 MB ~ L3) 1,970,964 MB/sec 108,466 MB/sec 18 10.00% 10.00% +34.00%
    PassMark single-thread CPU 3,710 Mops/s 2,365 Mops/s 1.5 10.00% 10.00% +4.10%

    GPU Bandwidth and Latency

    Node (all GPUs)
    Node baseline directional bandwidth
    		101.9 GB/s
    Node GPU-to-host bandwidth
    		113.2 GB/s
    Node host-to-GPU bandwidth
    		115.8 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
    		676 ns
    Per-GPU device memory copy bandwidth
    		730.3 GB/s
    Benchmark Environment
    Driver Version
    		 595.91.07
    CUDA Version (driver)
    		 13.2
    nvbandwidth Version
    		 v0.8
    GPU Count
    		 2
    P2P Supported
    No
    Efficiency
    SM/CE copy efficiency
    		0.93

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 2,686

    Geekbench Multi-Core

    Score: 24,576

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 79,378
    Compression
    		 1,051,451
    Encryption
    		 50,067
    Extended Instructions
    		 97,643
    Floating Point Maths
    		 240,024
    Integer Maths
    		 239,859
    Physics
    		 15,538
    Prime Numbers
    		 904
    Single Threaded
    		 3,710
    String Sorting
    		 141,568

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 2,356
    Database Operations
    		 37,230
    Memory Latency
    		 108
    Memory Read Cached
    		 33,469
    Memory Read Uncached
    		 30,267
    Memory Write
    		 30,256

    Stress-ng Stressors

    CPU integerSingleMultiScaling
    atomic
    		 481.63 378.06 0.78×
    bitops
    		 228,430 7,243,378 31.71×
    branch
    		 181,304 5,710,767 31.50×
    funccall
    		 893.8 28,380 31.75×
    funcret
    		 26,852 844,375 31.45×
    hash
    		 215,323 6,829,563 31.72×
    intmath
    		 78,163 2,491,473 31.88×
    nop
    		 423,789 13,411,018 31.65×
    prime
    		 607,461 19,654,435 32.36×
    rotate
    		 140,378 4,468,570 31.83×
    str
    		 1,585,915 49,453,232 31.18×
    wcs
    		 1,018,754 33,602,374 32.98×
    CryptographySingleMultiScaling
    crypt
    		 5,377 170,144 31.64×
    CompressionSingleMultiScaling
    jpeg
    		 1,233 38,630 31.32×
    zlib
    		 79.25 2,362 29.80×
    HypervisorSingleMultiScaling
    clock
    		 75,507 193,140 2.56×
    clone
    		 268.94 7,785 28.95×
    context
    		 8,327 269,406 32.35×
    cpu-sched
    		 66.28 2,055 31.01×
    eventfd
    		 70,121 1,030,621 14.70×
    fault
    		 39,191 119,377 3.05×
    fork
    		 4,509 49,516 10.98×
    getrandom
    		 97,545 3,095,391 31.73×
    hrtimers
    		 713,546 2,386,604 3.34×
    mprotect
    		 463,025 10,735,423 23.19×
    mtx
    		 29,018,363 2,732,322,318 94.16×
    munmap
    		 4,091 44,271 10.82×
    null
    		 1,405,370 44,619,060 31.75×
    pipe
    		 496,223 15,912,141 32.07×
    priv-instr
    		 1,368,588 8,856,150 6.47×
    resched
    		 7,777,189 14,424,152 1.85×
    switch
    		 93,342 13,257,312 142.03×
    timermix
    		 332,648 9,230,124 27.75×
    tlb-shootdown
    		 16,719 220,645 13.20×
    tsc
    		 875,097 27,816,955 31.79×
    usersyscall
    		 1,063,332 10,789,491 10.15×
    vdso
    		 96,737,241 3,068,593,133 31.72×
    vfork
    		 28,939 115,429 3.99×
    x86syscall
    		 18,616,815 588,493,281 31.61×
    yield
    		 42,993,981 64,241,585 1.49×
    zero
    		 10,838,825 343,241,301 31.67×
    CPU float/SIMDSingleMultiScaling
    eigen
    		 17,344 550,999 31.77×
    expmath
    		 3,941 125,880 31.94×
    fma
    		 1,540,474 49,213,289 31.95×
    fp
    		 191.3 6,518 34.07×
    fractal
    		 8.8 275.85 31.35×
    hyperbolic
    		 5,364 171,363 31.95×
    logmath
    		 5,570 178,794 32.10×
    matrix
    		 9,157 280,226 30.60×
    matrix-3d
    		 1,438 37,129 25.82×
    monte-carlo
    		 452.2 14,361 31.76×
    mpfr
    		 2,387 75,971 31.83×
    powmath
    		 1,811 57,977 32.01×
    trig
    		 2,413 76,494 31.70×
    veccmp
    		 29,900 948,857 31.73×
    vecfp
    		 2,399 75,088 31.30×
    vecmath
    		 4,676 149,241 31.91×
    vecshuf
    		 986.43 31,457 31.89×
    vecwide
    		 39,629 1,266,378 31.96×
    AlgorithmsSingleMultiScaling
    bitonicsort
    		 12.6 401.59 31.87×
    bsearch
    		 361.03 11,407 31.59×
    bubblesort
    		 1.2 38.4 32.00×
    fibsearch
    		 425.81 13,474 31.64×
    heapsort
    		 14.2 448.19 31.56×
    hsearch
    		 13,030 423,453 32.50×
    insertionsort
    		 15.2 448.2 29.49×
    malloc
    		 5,183,295 46,107,228 8.90×
    mcontend
    		 71.42 4,014 56.20×
    mergesort
    		 38.6 1,225 31.73×
    qsort
    		 25.8 829.77 32.16×
    skiplist
    		 8,337 264,506 31.73×
    tree
    		 2.6 77.71 29.89×
    MemorySingleMultiScaling
    cache
    		 1,159,526 1,255,492 1.08×
    cachehammer
    		 213,241 5,398,961 25.32×
    cacheline
    		 73.15 3,053 41.73×
    l1cache
    		 665.83 22,092 33.18×
    memcpy
    		 795.92 25,486 32.02×
    memrate
    		 0.73 20.17 27.63×
    memthrash
    		 147.85 1,665 11.26×
    ptr-chase
    		 75,654,573 1,245,995,541 16.47×
    spinmem
    		 402.18 2,599 6.46×
    stream
    		 408.41 92,752 227.11×
    vm
    		 239,187 295,089 1.23×

    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-32xCPU-160GB-2xRTXPRO6000 FAQs