GPU-12xCPU-128GB-2xL4 by UpCloud

GPU-12xCPU-128GB-2xL4 is a GPU (12 vCPUs, 128 GiB RAM, 2x L4) server offered by UpCloud with 12 vCPUs, 128 GiB of memory and 0 GB of storage. The last known price was 1.3096 USD per hour.
12 vCPU
128 GiB Memory
2 GPU
Spare SCore
45,720
(All-cores)
3,942
(Single-core)

Specifications

Server Metadata

Vendor ID
upcloud
Name
GPU-12xCPU-128GB-2xL4
Description
GPU (12 vCPUs, 128 GiB RAM, 2x L4)
Family
GPU
Hw Virt
Status
inactive
Observed At
2026-10-26T04:15:07.618903

Availability

REGION / IDSPOTONDEMAND
Sydney #1 (AU) / au-syd1
1.3096 USD/h 1.3209 USD/h
Frankfurt #1 (DE) / de-fra1
1.3096 USD/h 1.3209 USD/h
Copenhagen #1 (DK) / dk-cph1
1.3096 USD/h 1.3209 USD/h
Madrid #1 (ES) / es-mad1
1.3096 USD/h 1.3209 USD/h
Helsinki #1 (FI) / fi-hel1
1.3096 USD/h 1.3209 USD/h
Helsinki #2 (FI) / fi-hel2
1.3096 USD/h 1.3209 USD/h
Amsterdam #1 (NL) / nl-ams1
1.3096 USD/h 1.3209 USD/h
Stavanger #1 (NO) / no-svg1
1.3096 USD/h 1.3209 USD/h
Warsaw #1 (PL) / pl-waw1
1.3096 USD/h 1.3209 USD/h
Stockholm #1 (SE) / se-sto1
1.3096 USD/h 1.3209 USD/h
Singapore #1 (SG) / sg-sin1
1.3096 USD/h 1.3209 USD/h
London #1 (GB) / uk-lon1
1.3096 USD/h 1.3209 USD/h
Chicago #1 (US) / us-chi1
1.3096 USD/h 1.3209 USD/h
New York #1 (US) / us-nyc1
1.3096 USD/h 1.3209 USD/h
San Jose #1 (US) / us-sjo1
1.3096 USD/h 1.3209 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
11.6
Scalability
96.67

System Resources and Accelerators

MEMORY
Memory Amount
128 GiB
Memory Amount Actual
128 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
    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 dual-GPU accelerated virtual server featuring AMD EPYC processors and high memory density for parallel computing and machine learning inference.

      GPU AcceleratedMemory OptimizedCompute Optimized

      The UpCloud GPU-12xCPU-128GB-2xL4 is a KVM-based, GPU-accelerated server designed for memory-intensive and parallel computing workloads. It is configured with an AMD EPYC 9575F processor offering 12 shared vCPUs at 2.0 GHz, 128.0 GB of system memory, and dual NVIDIA L4 Ada Lovelace GPUs with a total of 48 GB VRAM. No local storage is included. Benchmarks show top-tier single-core CPU performance, with stress-ng single-core and single-threaded compression tests scoring in the top 10%. Additionally, it delivers top-tier text generation speeds of 349.81 tokens/sec for small LLM models. Multi-core CPU and memory bandwidth metrics remain in the average tier. This server is well-suited for machine learning inference, graphics rendering, and data science workloads that leverage dual-GPU acceleration and high system memory density.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      1.8Score
      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) 3,754,438 ops/sec 1,919,289 ops/sec 2 50.00% 50.00% +41.00%
      Redis RPS (pipeline=16, SET) 25,663,000 ops/sec 11,728,058 ops/sec 2.2 20.00% 20.00% +17.00%
      PassMark Memory Mark (composite) 2,438 2,416 1 10.00% 10.00% 0.00%
      Memory bandwidth (read, 16 MB ~ L3) 159,583 MB/sec 108,466 MB/sec 1.5 10.00% 10.00% +4.10%
      PassMark single-thread CPU 3,923 Mops/s 2,365 Mops/s 1.6 10.00% 10.00% +4.80%

      Memory Bandwidth

      Compression

      OpenSSL

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 35,207
      Compression
      		 383,295
      Encryption
      		 19,704
      Extended Instructions
      		 33,232
      Floating Point Maths
      		 88,756
      Integer Maths
      		 78,648
      Physics
      		 5,548
      Prime Numbers
      		 300
      Single Threaded
      		 3,923
      String Sorting
      		 51,535

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2,438
      Database Operations
      		 14,408
      Memory Latency
      		 102
      Memory Read Cached
      		 33,231
      Memory Read Uncached
      		 31,574
      Memory Write
      		 31,125

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 515.98 403.38 0.78×
      bitops
      		 238,734 2,614,988 10.95×
      branch
      		 179,918 2,046,445 11.37×
      funccall
      		 920.73 9,581 10.41×
      funcret
      		 27,589 302,566 10.97×
      hash
      		 199,139 2,326,988 11.69×
      intmath
      		 80,813 922,199 11.41×
      nop
      		 412,720 3,929,508 9.52×
      prime
      		 616,632 6,567,556 10.65×
      rotate
      		 143,421 1,397,966 9.75×
      str
      		 1,583,347 16,273,457 10.28×
      wcs
      		 959,082 10,363,212 10.81×
      CryptographySingleMultiScaling
      crypt
      		 5,509 58,717 10.66×
      CompressionSingleMultiScaling
      jpeg
      		 1,207 13,227 10.96×
      zlib
      		 84.29 889.51 10.55×
      HypervisorSingleMultiScaling
      clock
      		 79,287 279,701 3.53×
      clone
      		 443.45 4,102 9.25×
      context
      		 9,186 102,951 11.21×
      cpu-sched
      		 63.71 795.49 12.49×
      eventfd
      		 87,592 2,199,983 25.12×
      fault
      		 35,589 167,063 4.69×
      fork
      		 6,745 52,368 7.76×
      getrandom
      		 96,836 1,044,222 10.78×
      hrtimers
      		 147,694 2,475,204 16.76×
      mprotect
      		 748,297 6,243,728 8.34×
      mtx
      		 56,005,744 1,025,936,299 18.32×
      munmap
      		 5,460 48,476 8.88×
      null
      		 1,465,804 15,961,014 10.89×
      pipe
      		 711,297 10,782,124 15.16×
      priv-instr
      		 1,388,017 10,478,521 7.55×
      resched
      		 10,637,746 6,029,945 0.57×
      switch
      		 157,095 4,763,225 30.32×
      timermix
      		 326,230 3,486,123 10.69×
      tlb-shootdown
      		 23,268 99,041 4.26×
      tsc
      		 927,946 10,896,076 11.74×
      usersyscall
      		 1,094,571 9,847,202 9.00×
      vdso
      		 98,772,129 1,106,387,608 11.20×
      vfork
      		 47,024 206,632 4.39×
      x86syscall
      		 19,816,589 217,686,358 10.99×
      yield
      		 16,640,524 18,368,312 1.10×
      zero
      		 8,118,063 89,930,164 11.08×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 17,944 199,580 11.12×
      expmath
      		 4,185 46,352 11.07×
      fma
      		 1,591,872 17,035,234 10.70×
      fp
      		 189.6 2,251 11.87×
      fractal
      		 9.2 101.6 11.04×
      hyperbolic
      		 5,381 58,346 10.84×
      logmath
      		 5,531 63,667 11.51×
      matrix
      		 9,227 84,409 9.15×
      matrix-3d
      		 1,088 9,096 8.36×
      monte-carlo
      		 464.07 5,090 10.97×
      mpfr
      		 2,430 25,621 10.54×
      powmath
      		 1,845 21,709 11.77×
      trig
      		 2,358 27,369 11.61×
      veccmp
      		 30,142 296,054 9.82×
      vecfp
      		 2,475 28,892 11.67×
      vecmath
      		 4,744 52,181 11.00×
      vecshuf
      		 1,025 10,515 10.26×
      vecwide
      		 42,222 464,019 10.99×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 13.2 143 10.83×
      bsearch
      		 380.21 4,143 10.90×
      bubblesort
      		 1.4 16.4 11.71×
      fibsearch
      		 426.66 4,767 11.17×
      heapsort
      		 14.2 157.2 11.07×
      hsearch
      		 12,509 121,886 9.74×
      insertionsort
      		 15 144.4 9.63×
      malloc
      		 3,764,307 25,906,266 6.88×
      mcontend
      		 153.45 1,847 12.04×
      mergesort
      		 39.6 431.39 10.89×
      qsort
      		 26 282.2 10.85×
      skiplist
      		 8,130 92,376 11.36×
      tree
      		 2.2 20.19 9.18×
      MemorySingleMultiScaling
      cache
      		 1,216,390 1,323,078 1.09×
      cachehammer
      		 282,287 3,020,755 10.70×
      cacheline
      		 56.32 585.16 10.39×
      l1cache
      		 681.82 7,443 10.92×
      memcpy
      		 815.32 8,308 10.19×
      memrate
      		 1.11 9.88 8.90×
      memthrash
      		 163.56 747.99 4.57×
      ptr-chase
      		 21,357,591 48,604,773 2.28×
      spinmem
      		 430.18 828.09 1.92×
      stream
      		 451.07 23,871 52.92×
      vm
      		 242,208 293,185 1.21×

      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

      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-2xL4 FAQs