GPU-12xCPU-128GB-1xL40S by UpCloud

GPU-12xCPU-128GB-1xL40S is a GPU (12 vCPUs, 128 GiB RAM, 1x L40S) server offered by UpCloud with 12 vCPUs, 128 GiB of memory and 0 GB of storage. The pricing starts at 1.0521 USD per hour.
12 vCPU
128 GiB Memory
1 GPU
Spare SCore
50,451
(All-cores)
4,197
(Single-core)

Specifications

Server Metadata

Vendor ID
upcloud
Name
GPU-12xCPU-128GB-1xL40S
Description
GPU (12 vCPUs, 128 GiB RAM, 1x L40S)
Family
GPU
Hw Virt
Average Time To Start
73
Status
active
Observed At
2026-10-23T19:09:53.577181

Availability

REGION / IDSPOTONDEMAND
Helsinki #2 (FI) / fi-hel2
1.0521 USD/h 1.3991 USD/h

Processor

vCPUs
12
Hypervisor
KVM
CPU Allocation
Shared
CPU Cores
12
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
768 KiB
CPU L1I Cache
64 KiB
CPU L1I Cache Total
768 KiB
CPU L2 Cache
512 KiB
CPU L2 Cache Total
6 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
12
Scalability
100

System Resources and Accelerators

MEMORY
Memory Amount
128 GiB
Memory Amount Actual
128 GiB
ACCELERATORS
Accelerator Count
1
Accelerator Memory Min
48 GiB
Accelerator Memory Total
48 GiB
Accelerator Type
GPU
Accelerator Manufacturer
NVIDIA
Accelerator Family
Ada Lovelace
Accelerator Model
L40S
Accelerators
  • NVIDIA Ada Lovelace NVIDIA L40S (Memory amount: 46068, Firmware version: 595.71.05, BIOS version: 95.02.66.00.02, Clock rate: 2520)
STORAGE
Storage Size
0 GB
Storages
    NETWORK
    Inbound Traffic
    0 GB/month
    Outbound Traffic
    16384 GB/month
    IPv4
    1

    CPU and System Topology

    Server Description

    A GPU-accelerated virtual server combining top-tier single-core CPU performance with an NVIDIA L40S GPU for efficient machine learning inference.

    GPU AcceleratedMemory OptimizedCompute Optimized

    UpCloud GPU-12xCPU-128GB-1xL40S is a GPU-accelerated virtual server featuring 12 shared AMD EPYC 9575F vCPUs on the x86_64 architecture and 128.0 GB of system memory. It integrates a single NVIDIA L40S GPU with 48 GB of VRAM, based on the Ada Lovelace architecture. Benchmark data reveals top-tier single-core performance and strong large-block memory bandwidth, alongside highly efficient LLM inference capabilities, particularly in text generation. However, the instance does not include local storage, and the CPU cores are shared, which represents a tradeoff for sustained multi-core workloads. This server is highly suited for machine learning inference, image processing, and memory-intensive applications requiring moderate compute resources paired with high-performance graphics acceleration.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    2.6Score
    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) 4,928,217 ops/sec 1,919,289 ops/sec 2.6 50.00% 50.00% +61.00%
    Redis RPS (pipeline=16, SET) 31,633,490 ops/sec 11,728,058 ops/sec 2.7 20.00% 20.00% +22.00%
    PassMark Memory Mark (composite) 2,640 2,416 1.1 10.00% 10.00% +0.96%
    Memory bandwidth (read, 16 MB ~ L3) 1,014,040 MB/sec 108,466 MB/sec 9.1 10.00% 10.00% +25.00%
    PassMark single-thread CPU 4,230 Mops/s 2,365 Mops/s 1.8 10.00% 10.00% +6.10%

    GPU Bandwidth and Latency

    Node (all GPUs)
    Node baseline directional bandwidth
    		22.6 GB/s
    Node GPU-to-host bandwidth
    		26.4 GB/s
    Node host-to-GPU bandwidth
    		26.9 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
    		599 ns
    Benchmark Environment
    Driver Version
    		 595.71.05
    CUDA Runtime Version
    		 13.2
    nvbandwidth Version
    		 v0.8
    GPU Count
    		 1
    P2P Supported
    No
    Efficiency
    SM/CE copy efficiency
    		1.00

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 2,722

    Geekbench Multi-Core

    Score: 16,649

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 41,274
    Compression
    		 444,103
    Encryption
    		 21,318
    Extended Instructions
    		 39,684
    Floating Point Maths
    		 102,431
    Integer Maths
    		 102,308
    Physics
    		 6,665
    Prime Numbers
    		 402
    Single Threaded
    		 4,230
    String Sorting
    		 60,522

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 2,640
    Database Operations
    		 18,015
    Memory Latency
    		 96
    Memory Read Cached
    		 38,001
    Memory Read Uncached
    		 35,203
    Memory Write
    		 35,275

    Stress-ng Stressors

    CPU integerSingleMultiScaling
    atomic
    		 548.75 434.91 0.79×
    bitops
    		 253,560 3,043,391 12.00×
    branch
    		 195,348 2,343,997 12.00×
    funccall
    		 993.62 11,760 11.84×
    funcret
    		 30,488 351,905 11.54×
    hash
    		 240,781 2,872,480 11.93×
    intmath
    		 87,754 1,054,633 12.02×
    nop
    		 478,594 5,644,875 11.79×
    prime
    		 669,057 7,999,043 11.96×
    rotate
    		 153,365 1,864,943 12.16×
    str
    		 1,632,287 20,398,567 12.50×
    wcs
    		 1,127,564 13,614,392 12.07×
    CryptographySingleMultiScaling
    crypt
    		 5,956 69,503 11.67×
    CompressionSingleMultiScaling
    jpeg
    		 1,411 16,494 11.69×
    zlib
    		 86.66 973.15 11.23×
    HypervisorSingleMultiScaling
    clock
    		 87,918 280,662 3.19×
    clone
    		 540.97 4,414 8.16×
    context
    		 9,728 116,404 11.97×
    cpu-sched
    		 58.88 753.69 12.80×
    eventfd
    		 90,802 2,381,012 26.22×
    fault
    		 43,110 161,383 3.74×
    fork
    		 7,708 57,815 7.50×
    getrandom
    		 110,317 1,297,830 11.76×
    hrtimers
    		 123,810 1,548,928 12.51×
    mprotect
    		 736,594 6,478,897 8.80×
    mtx
    		 58,356,653 1,148,251,604 19.68×
    munmap
    		 6,181 49,924 8.08×
    null
    		 1,633,413 19,334,616 11.84×
    pipe
    		 680,554 10,269,154 15.09×
    priv-instr
    		 1,501,051 10,060,606 6.70×
    resched
    		 10,319,845 5,758,224 0.56×
    switch
    		 127,275 5,682,502 44.65×
    timermix
    		 365,893 4,316,373 11.80×
    tlb-shootdown
    		 20,523 116,124 5.66×
    tsc
    		 956,963 11,573,252 12.09×
    usersyscall
    		 1,189,470 8,649,484 7.27×
    vdso
    		 109,495,283 1,308,643,937 11.95×
    vfork
    		 47,993 186,777 3.89×
    x86syscall
    		 20,970,806 249,355,273 11.89×
    yield
    		 18,858,525 22,034,086 1.17×
    zero
    		 8,790,193 103,405,539 11.76×
    CPU float/SIMDSingleMultiScaling
    eigen
    		 19,445 231,994 11.93×
    expmath
    		 4,412 52,589 11.92×
    fma
    		 1,735,221 20,402,675 11.76×
    fp
    		 202.79 2,727 13.45×
    fractal
    		 9.8 115.2 11.76×
    hyperbolic
    		 6,014 71,190 11.84×
    logmath
    		 6,355 74,735 11.76×
    matrix
    		 10,320 120,092 11.64×
    matrix-3d
    		 1,452 14,001 9.64×
    monte-carlo
    		 506.7 5,951 11.74×
    mpfr
    		 2,673 31,126 11.64×
    powmath
    		 2,024 24,224 11.97×
    trig
    		 2,654 31,640 11.92×
    veccmp
    		 32,929 390,343 11.85×
    vecfp
    		 2,692 31,899 11.85×
    vecmath
    		 5,277 61,122 11.58×
    vecshuf
    		 1,112 13,127 11.81×
    vecwide
    		 44,461 515,086 11.59×
    AlgorithmsSingleMultiScaling
    bitonicsort
    		 14.2 162.6 11.45×
    bsearch
    		 394.59 4,810 12.19×
    bubblesort
    		 1.4 17.4 12.43×
    fibsearch
    		 465.88 5,586 11.99×
    heapsort
    		 15.8 186 11.77×
    hsearch
    		 14,438 173,087 11.99×
    insertionsort
    		 17.2 205 11.92×
    malloc
    		 5,531,640 34,464,471 6.23×
    mcontend
    		 124.08 2,046 16.49×
    mergesort
    		 42.6 506.98 11.90×
    qsort
    		 30 339.79 11.33×
    skiplist
    		 9,233 109,878 11.90×
    tree
    		 2.8 32.19 11.50×
    MemorySingleMultiScaling
    cache
    		 1,350,313 1,423,320 1.05×
    cachehammer
    		 288,749 3,206,641 11.11×
    cacheline
    		 70.36 701.71 9.97×
    l1cache
    		 754.6 8,905 11.80×
    memcpy
    		 897.17 10,616 11.83×
    memrate
    		 1.19 10.44 8.77×
    memthrash
    		 175.16 786.85 4.49×
    ptr-chase
    		 82,375,077 365,518,040 4.44×
    spinmem
    		 449.78 914.33 2.03×
    stream
    		 486.32 19,804 40.72×
    vm
    		 260,511 293,272 1.13×

    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-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
    GPU-20xCPU-256GB-1xL40S 20256 GiB1

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYAccelerators

    GPU-12xCPU-128GB-1xL40S FAQs