GPU-16xCPU-80GB-1xRTXPRO6000 by UpCloud

GPU-16xCPU-80GB-1xRTXPRO6000 is a GPU (16 vCPUs, 80 GiB RAM, 1x RTXPRO6000) server offered by UpCloud with 16 vCPUs, 80 GiB of memory and 0 GB of storage. The pricing starts at 0.972 USD per hour.
16 vCPU
80 GiB Memory
1 GPU
Spare SCore
59,279
(All-cores)
3,705
(Single-core)

Specifications

Server Metadata

Vendor ID
upcloud
Name
GPU-16xCPU-80GB-1xRTXPRO6000
Description
GPU (16 vCPUs, 80 GiB RAM, 1x RTXPRO6000)
Family
GPU
Hw Virt
Average Time To Start
55
Status
active
Observed At
2026-10-31T19:21:08.481320

Availability

REGION / IDSPOTONDEMAND
Helsinki #2 (FI) / fi-hel2
0.972 USD/h 1.8437 USD/h

Processor

vCPUs
16
Hypervisor
KVM
CPU Allocation
Shared
CPU Cores
16
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
1 MiB
CPU L1I Cache
64 KiB
CPU L1I Cache Total
1 MiB
CPU L2 Cache
512 KiB
CPU L2 Cache Total
8 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
16
Scalability
100

System Resources and Accelerators

MEMORY
Memory Amount
80 GiB
Memory Amount Actual
80 GiB
ACCELERATORS
Accelerator Count
1
Accelerator Memory Min
96 GiB
Accelerator Memory Total
96 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)
STORAGE
Storage Size
0 GB
Storages
    NETWORK
    Inbound Traffic
    0 GB/month
    Outbound Traffic
    36864 GB/month
    IPv4
    1

    CPU and System Topology

    Server Description

    A GPU-accelerated server featuring an NVIDIA Blackwell GPU with ninety-six gigabytes of VRAM for high-performance machine learning and inference workloads.

    GPU AcceleratedCompute Optimized

    The UpCloud GPU-16xCPU-80GB-1xRTXPRO6000 is a KVM-based, GPU-accelerated server designed for compute-intensive workloads. It features an AMD EPYC 9555 processor with 16 physical cores (16 vCPUs) running at 2.0 GHz, paired with 80.0 GB of system memory. The primary accelerator is a single NVIDIA RTX PRO 6000 Blackwell Server Edition GPU with 96 GB of VRAM. This server does not include local storage. In benchmark testing, it demonstrates top-tier single-core CPU performance, high large-block memory bandwidth, and exceptional LLM inference speeds for small and medium models. Multi-core performance and physics simulations are also strong. Given its specialized hardware profile, this instance is highly suited for machine learning inference, image processing, and data science applications, offering a balanced ratio of system memory to high-capacity VRAM.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    2.9Score
    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) 5,447,452 ops/sec 1,918,343 ops/sec 2.8 50.00% 50.00% +67.00%
    Redis RPS (pipeline=16, SET) 37,243,592 ops/sec 11,704,734 ops/sec 3.1 20.00% 20.00% +25.00%
    PassMark Memory Mark (composite) 2,180 2,416 0.92 10.00% 10.00% -0.83%
    Memory bandwidth (read, 16 MB ~ L3) 2,008,989 MB/sec 108,466 MB/sec 18 10.00% 10.00% +34.00%
    PassMark single-thread CPU 3,732 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
    		50.9 GB/s
    Node GPU-to-host bandwidth
    		56.6 GB/s
    Node host-to-GPU bandwidth
    		57.9 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
    		669 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
    		 1
    P2P Supported
    No
    Efficiency
    SM/CE copy efficiency
    		0.93

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 2,672

    Geekbench Multi-Core

    Score: 19,769

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 46,457
    Compression
    		 527,833
    Encryption
    		 25,031
    Extended Instructions
    		 48,498
    Floating Point Maths
    		 119,869
    Integer Maths
    		 119,883
    Physics
    		 7,832
    Prime Numbers
    		 446
    Single Threaded
    		 3,732
    String Sorting
    		 69,521

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 2,180
    Database Operations
    		 19,179
    Memory Latency
    		 118
    Memory Read Cached
    		 33,362
    Memory Read Uncached
    		 29,559
    Memory Write
    		 29,374

    Stress-ng Stressors

    CPU integerSingleMultiScaling
    atomic
    		 489.37 446.51 0.91×
    bitops
    		 227,074 3,629,034 15.98×
    branch
    		 181,327 2,866,538 15.81×
    funccall
    		 887.1 14,203 16.01×
    funcret
    		 26,493 434,840 16.41×
    hash
    		 215,025 3,418,411 15.90×
    intmath
    		 78,404 1,247,752 15.91×
    nop
    		 422,203 6,746,172 15.98×
    prime
    		 611,242 9,756,777 15.96×
    rotate
    		 140,219 2,229,252 15.90×
    str
    		 1,579,420 24,621,875 15.59×
    wcs
    		 1,025,601 16,916,878 16.49×
    CryptographySingleMultiScaling
    crypt
    		 5,361 84,486 15.76×
    CompressionSingleMultiScaling
    jpeg
    		 1,206 18,890 15.66×
    zlib
    		 74.44 1,142 15.33×
    HypervisorSingleMultiScaling
    clock
    		 79,088 174,612 2.21×
    clone
    		 372.42 3,915 10.51×
    context
    		 8,472 134,931 15.93×
    cpu-sched
    		 69.29 994.65 14.35×
    eventfd
    		 67,614 591,123 8.74×
    fault
    		 39,759 112,144 2.82×
    fork
    		 5,072 49,496 9.76×
    getrandom
    		 97,362 1,545,615 15.87×
    hrtimers
    		 213,925 1,809,982 8.46×
    mprotect
    		 455,164 6,771,452 14.88×
    mtx
    		 36,615,387 1,368,576,179 37.38×
    munmap
    		 3,770 32,057 8.50×
    null
    		 1,404,548 22,411,252 15.96×
    pipe
    		 572,737 8,688,933 15.17×
    priv-instr
    		 1,362,813 4,784,389 3.51×
    resched
    		 6,426,454 7,727,984 1.20×
    switch
    		 98,585 6,681,665 67.78×
    timermix
    		 332,889 4,949,369 14.87×
    tlb-shootdown
    		 14,736 116,688 7.92×
    tsc
    		 874,924 13,899,712 15.89×
    usersyscall
    		 1,057,607 5,104,538 4.83×
    vdso
    		 96,074,067 1,535,884,274 15.99×
    vfork
    		 17,627 71,303 4.05×
    x86syscall
    		 18,209,279 294,179,024 16.16×
    yield
    		 21,318,496 22,206,264 1.04×
    zero
    		 10,754,709 160,446,018 14.92×
    CPU float/SIMDSingleMultiScaling
    eigen
    		 17,251 275,609 15.98×
    expmath
    		 3,962 63,113 15.93×
    fma
    		 1,545,687 24,595,717 15.91×
    fp
    		 188.69 3,254 17.25×
    fractal
    		 8.8 138.01 15.68×
    hyperbolic
    		 5,398 85,617 15.86×
    logmath
    		 5,646 89,532 15.86×
    matrix
    		 9,176 141,152 15.38×
    matrix-3d
    		 1,318 19,441 14.75×
    monte-carlo
    		 452 7,207 15.94×
    mpfr
    		 2,383 38,063 15.97×
    powmath
    		 1,819 28,970 15.92×
    trig
    		 2,414 38,379 15.90×
    veccmp
    		 29,766 475,243 15.97×
    vecfp
    		 2,364 37,288 15.78×
    vecmath
    		 4,671 74,570 15.96×
    vecshuf
    		 988.57 15,757 15.94×
    vecwide
    		 39,918 631,646 15.82×
    AlgorithmsSingleMultiScaling
    bitonicsort
    		 12.8 201.8 15.77×
    bsearch
    		 360.41 5,724 15.88×
    bubblesort
    		 1.2 19.2 16.00×
    fibsearch
    		 421.22 6,751 16.03×
    heapsort
    		 14.2 225.59 15.89×
    hsearch
    		 13,275 209,842 15.81×
    insertionsort
    		 14.8 230.8 15.59×
    malloc
    		 4,713,783 26,650,051 5.65×
    mcontend
    		 75.01 1,989 26.51×
    mergesort
    		 38.4 614.98 16.02×
    qsort
    		 26.4 417.18 15.80×
    skiplist
    		 8,193 132,468 16.17×
    tree
    		 2.6 40.77 15.68×
    MemorySingleMultiScaling
    cache
    		 1,184,894 970,528 0.82×
    cachehammer
    		 172,220 2,663,625 15.47×
    cacheline
    		 40.17 685.99 17.08×
    l1cache
    		 683.65 10,877 15.91×
    memcpy
    		 798.7 12,721 15.93×
    memrate
    		 0.84 11.3 13.45×
    memthrash
    		 223.27 952.08 4.26×
    ptr-chase
    		 54,688,529 906,678,921 16.58×
    spinmem
    		 328.58 1,188 3.61×
    stream
    		 419.09 41,035 97.92×
    vm
    		 212,219 293,164 1.38×

    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-192GB-1xL4 16192 GiB1

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYAccelerators

    GPU-16xCPU-80GB-1xRTXPRO6000 FAQs