GPU-12xCPU-128GB-1xL4 by UpCloud

GPU-12xCPU-128GB-1xL4 is a GPU (12 vCPUs, 128 GiB RAM, 1x L4) server offered by UpCloud with 12 vCPUs, 128 GiB of memory and 0 GB of storage. The last known price was 0.7723 USD per hour.
12 vCPU
128 GiB Memory
1 GPU
Spare SCore
47,554
(All-cores)
4,036
(Single-core)

Specifications

Server Metadata

Vendor ID
upcloud
Name
GPU-12xCPU-128GB-1xL4
Description
GPU (12 vCPUs, 128 GiB RAM, 1x L4)
Family
GPU
Hw Virt
Average Time To Start
66.5
Status
inactive
Observed At
2026-10-26T00:49:33.834543

Availability

REGION / IDSPOTONDEMAND
Sydney #1 (AU) / au-syd1
0.7723 USD/h 0.7828 USD/h
Frankfurt #1 (DE) / de-fra1
0.7723 USD/h 0.7828 USD/h
Copenhagen #1 (DK) / dk-cph1
0.7723 USD/h 0.7828 USD/h
Madrid #1 (ES) / es-mad1
0.7723 USD/h 0.7828 USD/h
Helsinki #1 (FI) / fi-hel1
0.7723 USD/h 0.7828 USD/h
Helsinki #2 (FI) / fi-hel2
0.7723 USD/h 0.7828 USD/h
Amsterdam #1 (NL) / nl-ams1
0.7723 USD/h 0.7828 USD/h
Stavanger #1 (NO) / no-svg1
0.7723 USD/h 0.7828 USD/h
Warsaw #1 (PL) / pl-waw1
0.7723 USD/h 0.7828 USD/h
Stockholm #1 (SE) / se-sto1
0.7723 USD/h 0.7828 USD/h
Singapore #1 (SG) / sg-sin1
0.7723 USD/h 0.7828 USD/h
London #1 (GB) / uk-lon1
0.7723 USD/h 0.7828 USD/h
Chicago #1 (US) / us-chi1
0.7723 USD/h 0.7828 USD/h
New York #1 (US) / us-nyc1
0.7723 USD/h 0.7828 USD/h
San Jose #1 (US) / us-sjo1
0.7723 USD/h 0.7828 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
11.8
Scalability
98.33

System Resources and Accelerators

MEMORY
Memory Amount
128 GiB
Memory Amount Actual
128 GiB
ACCELERATORS
Accelerator Count
1
Accelerator Memory Min
24 GiB
Accelerator Memory Total
24 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: 595.71.05, BIOS version: 95.04.65.00.13, Clock rate: 2040)
STORAGE
Storage Size
0 GB
Storages
    NETWORK
    Inbound Traffic
    0 GB/month
    Outbound Traffic
    24576 GB/month
    IPv4
    1

    CPU and System Topology

    Server Description

    A GPU-accelerated server combining AMD EPYC processors and NVIDIA L4 graphics for memory-intensive parallel computing and machine learning workloads.

    GPU AcceleratedMemory OptimizedGeneral Purpose

    UpCloud GPU-12xCPU-128GB-1xL4 is a GPU-accelerated server featuring 12 vCPUs powered by AMD EPYC 9575F processors at 2.0 GHz, 128.0 GB of RAM, and a single NVIDIA L4 GPU with 24 GB of VRAM. Operating on the KVM hypervisor, this x86_64 system does not include local storage. Benchmarks show top-tier single-core CPU performance and text processing, alongside strong multi-core and large-block memory read capabilities. Text generation for small LLM models also ranks in the top tier. With 10.67 GB of RAM per core and dedicated Ada Lovelace GPU architecture, this instance provides a balanced resource profile for GPU-accelerated workloads. It is suited for small-scale machine learning inference, image processing, and memory-intensive computing tasks that utilize network-attached storage.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    2Score
    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) 3,839,445 ops/sec 1,919,289 ops/sec 2 50.00% 50.00% +41.00%
    Redis RPS (pipeline=16, SET) 24,596,015 ops/sec 11,728,058 ops/sec 2.1 20.00% 20.00% +16.00%
    PassMark Memory Mark (composite) 2,554 2,416 1.1 10.00% 10.00% +0.96%
    Memory bandwidth (read, 16 MB ~ L3) 422,756 MB/sec 108,466 MB/sec 3.8 10.00% 10.00% +14.00%
    PassMark single-thread CPU 3,938 Mops/s 2,365 Mops/s 1.6 10.00% 10.00% +4.80%

    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
    		586 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: 2,815

    Geekbench Multi-Core

    Score: 17,299

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 36,792
    Compression
    		 394,894
    Encryption
    		 20,000
    Extended Instructions
    		 33,688
    Floating Point Maths
    		 94,470
    Integer Maths
    		 89,603
    Physics
    		 5,507
    Prime Numbers
    		 327
    Single Threaded
    		 3,938
    String Sorting
    		 52,147

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 2,554
    Database Operations
    		 15,324
    Memory Latency
    		 97
    Memory Read Cached
    		 35,280
    Memory Read Uncached
    		 32,494
    Memory Write
    		 31,953

    Stress-ng Stressors

    CPU integerSingleMultiScaling
    atomic
    		 485.31 451.06 0.93×
    bitops
    		 237,869 2,732,501 11.49×
    branch
    		 181,536 2,087,495 11.50×
    funccall
    		 947.34 10,625 11.22×
    funcret
    		 27,944 318,594 11.40×
    hash
    		 225,585 2,656,301 11.78×
    intmath
    		 83,748 989,613 11.82×
    nop
    		 434,760 5,101,169 11.73×
    prime
    		 642,568 6,876,718 10.70×
    rotate
    		 146,730 1,747,587 11.91×
    str
    		 1,575,713 17,768,467 11.28×
    wcs
    		 1,070,657 12,024,120 11.23×
    CryptographySingleMultiScaling
    crypt
    		 5,740 60,758 10.58×
    CompressionSingleMultiScaling
    jpeg
    		 1,280 14,571 11.38×
    zlib
    		 74.13 844.04 11.39×
    HypervisorSingleMultiScaling
    clock
    		 84,456 289,119 3.42×
    clone
    		 534.44 4,514 8.45×
    context
    		 9,252 108,420 11.72×
    cpu-sched
    		 75.35 793.51 10.53×
    eventfd
    		 102,778 2,311,383 22.49×
    fault
    		 39,706 157,634 3.97×
    fork
    		 6,674 52,611 7.88×
    getrandom
    		 101,425 1,180,859 11.64×
    hrtimers
    		 315,803 2,368,383 7.50×
    mprotect
    		 683,426 6,188,630 9.06×
    mtx
    		 56,628,939 1,007,822,482 17.80×
    munmap
    		 5,099 48,509 9.51×
    null
    		 1,540,251 17,577,541 11.41×
    pipe
    		 1,512,651 10,413,706 6.88×
    priv-instr
    		 1,398,496 9,213,348 6.59×
    resched
    		 10,817,070 6,282,530 0.58×
    switch
    		 99,153 5,261,554 53.06×
    timermix
    		 353,480 4,101,433 11.60×
    tlb-shootdown
    		 25,240 106,214 4.21×
    tsc
    		 940,838 11,217,265 11.92×
    usersyscall
    		 1,139,058 10,376,573 9.11×
    vdso
    		 101,482,391 1,197,284,554 11.80×
    vfork
    		 51,811 206,085 3.98×
    x86syscall
    		 19,504,708 231,316,898 11.86×
    yield
    		 18,385,359 19,356,739 1.05×
    zero
    		 8,344,057 93,483,656 11.20×
    CPU float/SIMDSingleMultiScaling
    eigen
    		 18,207 207,038 11.37×
    expmath
    		 4,070 49,155 12.08×
    fma
    		 1,619,529 19,450,944 12.01×
    fp
    		 228.9 2,548 11.13×
    fractal
    		 9.2 108.41 11.78×
    hyperbolic
    		 5,724 66,129 11.55×
    logmath
    		 6,028 69,592 11.55×
    matrix
    		 9,446 106,235 11.25×
    matrix-3d
    		 1,232 12,989 10.55×
    monte-carlo
    		 485.21 5,332 10.99×
    mpfr
    		 2,460 28,453 11.57×
    powmath
    		 1,918 22,960 11.97×
    trig
    		 2,520 28,651 11.37×
    veccmp
    		 31,344 359,376 11.47×
    vecfp
    		 2,619 30,078 11.48×
    vecmath
    		 5,008 58,360 11.65×
    vecshuf
    		 1,041 11,806 11.34×
    vecwide
    		 41,809 445,703 10.66×
    AlgorithmsSingleMultiScaling
    bitonicsort
    		 12.4 149.2 12.03×
    bsearch
    		 373.98 4,270 11.42×
    bubblesort
    		 1.4 16.8 12.00×
    fibsearch
    		 424.66 5,063 11.92×
    heapsort
    		 15 167.39 11.16×
    hsearch
    		 13,411 146,360 10.91×
    insertionsort
    		 16.4 185.6 11.32×
    malloc
    		 4,889,579 27,970,878 5.72×
    mcontend
    		 133.06 2,080 15.63×
    mergesort
    		 39.8 460.19 11.56×
    qsort
    		 28.2 320.59 11.37×
    skiplist
    		 8,807 96,708 10.98×
    tree
    		 2.6 24.79 9.53×
    MemorySingleMultiScaling
    cache
    		 1,243,708 1,309,348 1.05×
    cachehammer
    		 279,034 3,088,698 11.07×
    cacheline
    		 52.27 645.49 12.35×
    l1cache
    		 708.96 8,269 11.66×
    memcpy
    		 836.28 9,194 10.99×
    memrate
    		 1.16 9.5 8.19×
    memthrash
    		 199.32 773.49 3.88×
    ptr-chase
    		 21,764,880 111,143,487 5.11×
    spinmem
    		 426.38 906.94 2.13×
    stream
    		 443.69 24,820 55.94×
    vm
    		 244,180 293,209 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-12xCPU-128GB-1xL4 FAQs