GPU-16xCPU-192GB-2xL4 by UpCloud

GPU-16xCPU-192GB-2xL4 is a GPU (16 vCPUs, 192 GiB RAM, 2x L4) server offered by UpCloud with 16 vCPUs, 192 GiB of memory and 0 GB of storage. The last known price was 1.4433 USD per hour.
16 vCPU
192 GiB Memory
2 GPU
Spare SCore
63,128
(All-cores)
4,003
(Single-core)

Specifications

Server Metadata

Vendor ID
upcloud
Name
GPU-16xCPU-192GB-2xL4
Description
GPU (16 vCPUs, 192 GiB RAM, 2x L4)
Family
GPU
Hw Virt
Average Time To Start
76
Status
inactive
Observed At
2026-10-27T01:09:14.416916

Availability

REGION / IDSPOTONDEMAND
Sydney #1 (AU) / au-syd1
1.4433 USD/h 1.4551 USD/h
Frankfurt #1 (DE) / de-fra1
1.4433 USD/h 1.4551 USD/h
Copenhagen #1 (DK) / dk-cph1
1.4433 USD/h 1.4551 USD/h
Madrid #1 (ES) / es-mad1
1.4433 USD/h 1.4551 USD/h
Helsinki #1 (FI) / fi-hel1
1.4433 USD/h 1.4551 USD/h
Helsinki #2 (FI) / fi-hel2
1.4433 USD/h 1.4551 USD/h
Amsterdam #1 (NL) / nl-ams1
1.4433 USD/h 1.4551 USD/h
Stavanger #1 (NO) / no-svg1
1.4433 USD/h 1.4551 USD/h
Warsaw #1 (PL) / pl-waw1
1.4433 USD/h 1.4551 USD/h
Stockholm #1 (SE) / se-sto1
1.4433 USD/h 1.4551 USD/h
Singapore #1 (SG) / sg-sin1
1.4433 USD/h 1.4551 USD/h
London #1 (GB) / uk-lon1
1.4433 USD/h 1.4551 USD/h
Chicago #1 (US) / us-chi1
1.4433 USD/h 1.4551 USD/h
New York #1 (US) / us-nyc1
1.4433 USD/h 1.4551 USD/h
San Jose #1 (US) / us-sjo1
1.4433 USD/h 1.4551 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
9575F
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, 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, avx512_vp2intersect, arch_capabilities
Ecpus
15.8
Scalability
98.75

System Resources and Accelerators

MEMORY
Memory Amount
192 GiB
Memory Amount Actual
192 GiB
ACCELERATORS
Accelerator Count
2
Accelerator Memory Min
24 GiB
Accelerator Memory Total
48 GiB
Accelerator Type
GPU
Accelerator Manufacturer
NVIDIA
Accelerator Family
Ada Lovelace
Accelerator Model
L4
Accelerators
  • NVIDIA Ada Lovelace NVIDIA L4 (Memory amount: 23034, Firmware version: 595.84, BIOS version: 95.04.65.00.13, Clock rate: 2040)
  • NVIDIA Ada Lovelace NVIDIA L4 (Memory amount: 23034, Firmware version: 595.84, BIOS version: 95.04.65.00.13, Clock rate: 2040)
STORAGE
Storage Size
0 GB
Storages
    NETWORK
    Inbound Traffic
    0 GB/month
    Outbound Traffic
    28672 GB/month
    IPv4
    1

    CPU and System Topology

    Server Description

    A dual-GPU accelerated virtual server with high memory density, optimized for machine learning inference and parallel computing workloads.

    GPU AcceleratedMemory Optimized

    UpCloud GPU-16xCPU-192GB-2xL4 is a KVM-based virtual server designed for GPU-accelerated and memory-intensive workloads. It features 16 vCPUs powered by an AMD EPYC 9575F processor, 192.0 GB of system memory, and two NVIDIA L4 GPUs with 48 GB of total VRAM. The server lacks local storage, requiring external block storage solutions. Benchmark data highlights top-tier single-core CPU performance and exceptional LLM inference speeds, processing 2806.44 tokens/sec for prompt processing on a 7B model. Large-block memory bandwidth and multi-core CPU performance are also strong, ranking in the top 25%. This hardware profile is highly suited for machine learning inference, data science pipelines, and parallelized scientific computing.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    2.5Score
    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) 5,501,326 ops/sec 1,918,343 ops/sec 2.9 50.00% 50.00% +70.00%
    Redis RPS (pipeline=16, SET) 30,719,730 ops/sec 11,704,734 ops/sec 2.6 20.00% 20.00% +21.00%
    PassMark Memory Mark (composite) 2,420 2,416 1 10.00% 10.00% 0.00%
    Memory bandwidth (read, 16 MB ~ L3) 453,025 MB/sec 108,420 MB/sec 4.1 10.00% 10.00% +15.00%
    PassMark single-thread CPU 3,992 Mops/s 2,365 Mops/s 1.7 10.00% 10.00% +5.40%

    GPU Bandwidth and Latency

    Node (all GPUs)
    Node baseline directional bandwidth
    		45.3 GB/s
    Node GPU-to-host bandwidth
    		52.7 GB/s
    Node host-to-GPU bandwidth
    		53.7 GB/s
    Single GPU slot
    Per-GPU GPU-to-host bandwidth
    		26.4 GB/s
    Per-GPU host-to-GPU bandwidth
    		26.9 GB/s
    Per-GPU host-device latency
    		587 ns
    Benchmark Environment
    Driver Version
    		 595.84
    CUDA Runtime Version
    		 13.2
    nvbandwidth Version
    		 v0.8
    GPU Count
    		 2
    P2P Supported
    No
    Efficiency
    SM/CE copy efficiency
    		1.00

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 2,812

    Geekbench Multi-Core

    Score: 20,488

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 47,382
    Compression
    		 523,473
    Encryption
    		 26,014
    Extended Instructions
    		 44,832
    Floating Point Maths
    		 124,527
    Integer Maths
    		 126,417
    Physics
    		 7,125
    Prime Numbers
    		 436
    Single Threaded
    		 3,992
    String Sorting
    		 70,427

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 2,420
    Database Operations
    		 20,451
    Memory Latency
    		 105
    Memory Read Cached
    		 34,430
    Memory Read Uncached
    		 31,892
    Memory Write
    		 31,878

    Stress-ng Stressors

    CPU integerSingleMultiScaling
    atomic
    		 512.33 452.15 0.88×
    bitops
    		 245,187 3,750,683 15.30×
    branch
    		 191,224 2,930,311 15.32×
    funccall
    		 939.41 13,941 14.84×
    funcret
    		 29,308 440,655 15.04×
    hash
    		 223,692 3,635,990 16.25×
    intmath
    		 83,976 1,333,780 15.88×
    nop
    		 443,182 7,087,235 15.99×
    prime
    		 621,539 9,529,512 15.33×
    rotate
    		 145,837 2,325,081 15.94×
    str
    		 1,605,095 24,029,226 14.97×
    wcs
    		 1,053,302 16,238,100 15.42×
    CryptographySingleMultiScaling
    crypt
    		 5,701 85,582 15.01×
    CompressionSingleMultiScaling
    jpeg
    		 1,310 19,900 15.19×
    zlib
    		 61.38 1,187 19.34×
    HypervisorSingleMultiScaling
    clock
    		 84,540 286,336 3.39×
    clone
    		 416.59 5,059 12.14×
    context
    		 9,106 143,413 15.75×
    cpu-sched
    		 62.68 1,038 16.56×
    eventfd
    		 109,224 877,312 8.03×
    fault
    		 38,808 171,769 4.43×
    fork
    		 6,744 63,540 9.42×
    getrandom
    		 101,456 1,521,534 15.00×
    hrtimers
    		 205,621 3,689,086 17.94×
    mprotect
    		 754,969 8,374,665 11.09×
    mtx
    		 32,523,115 1,418,115,430 43.60×
    munmap
    		 5,419 52,855 9.75×
    null
    		 1,521,344 23,685,372 15.57×
    pipe
    		 676,419 14,329,743 21.18×
    priv-instr
    		 1,438,015 11,582,922 8.05×
    resched
    		 14,078,505 8,828,831 0.63×
    switch
    		 129,011 7,367,177 57.10×
    timermix
    		 232,460 5,431,657 23.37×
    tlb-shootdown
    		 23,988 127,567 5.32×
    tsc
    		 947,409 15,044,699 15.88×
    usersyscall
    		 1,160,490 11,614,339 10.01×
    vdso
    		 105,012,220 1,628,686,818 15.51×
    vfork
    		 47,862 205,619 4.30×
    x86syscall
    		 19,903,746 310,930,587 15.62×
    yield
    		 25,228,521 25,754,289 1.02×
    zero
    		 8,281,218 127,694,712 15.42×
    CPU float/SIMDSingleMultiScaling
    eigen
    		 18,330 290,007 15.82×
    expmath
    		 4,284 66,366 15.49×
    fma
    		 1,662,266 25,797,446 15.52×
    fp
    		 206.4 3,449 16.71×
    fractal
    		 9.4 146.61 15.60×
    hyperbolic
    		 5,672 89,184 15.72×
    logmath
    		 5,861 92,957 15.86×
    matrix
    		 9,382 138,958 14.81×
    matrix-3d
    		 1,469 14,005 9.53×
    monte-carlo
    		 473.83 7,405 15.63×
    mpfr
    		 2,549 38,980 15.29×
    powmath
    		 1,949 30,205 15.50×
    trig
    		 2,512 39,541 15.74×
    veccmp
    		 31,798 475,076 14.94×
    vecfp
    		 2,599 40,033 15.40×
    vecmath
    		 5,011 78,262 15.62×
    vecshuf
    		 1,066 16,119 15.12×
    vecwide
    		 42,823 630,049 14.71×
    AlgorithmsSingleMultiScaling
    bitonicsort
    		 13.2 200.6 15.20×
    bsearch
    		 386.55 5,980 15.47×
    bubblesort
    		 1.4 22.4 16.00×
    fibsearch
    		 453.51 6,938 15.30×
    heapsort
    		 15.4 232.99 15.13×
    hsearch
    		 13,817 204,787 14.82×
    insertionsort
    		 16.4 242.4 14.78×
    malloc
    		 4,652,950 34,649,036 7.45×
    mcontend
    		 141.69 2,876 20.30×
    mergesort
    		 41.2 627.78 15.24×
    qsort
    		 27.4 422.79 15.43×
    skiplist
    		 8,817 136,169 15.44×
    tree
    		 2.6 33.79 13.00×
    MemorySingleMultiScaling
    cache
    		 1,258,920 1,475,629 1.17×
    cachehammer
    		 272,691 4,062,409 14.90×
    cacheline
    		 68.07 1,003 14.74×
    l1cache
    		 729.31 11,013 15.10×
    memcpy
    		 849.72 12,644 14.88×
    memrate
    		 1.17 12.32 10.53×
    memthrash
    		 189.49 977.02 5.16×
    ptr-chase
    		 35,410,511 190,315,239 5.37×
    spinmem
    		 442.58 1,441 3.26×
    stream
    		 448.13 28,784 64.23×
    vm
    		 245,073 293,871 1.20×

    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-1xL40S 864 GiB1
    GPU-12xCPU-128GB-1xL40S 12128 GiB1
    GPU-12xCPU-128GB-2xL40S 12128 GiB2
    GPU-16xCPU-80GB-1xRTXPRO6000 1680 GiB1
    GPU-16xCPU-192GB-1xL40S 16192 GiB1
    GPU-16xCPU-192GB-2xL40S 16192 GiB2
    GPU-16xCPU-192GB-3xL40S 16192 GiB3

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYAccelerators

    GPU-16xCPU-192GB-2xL4 FAQs