c3d-highmem-4 by Google Cloud Platform

c3d-highmem-4 is a 4 vCPUs, 32 GB RAM server offered by Google Cloud Platform with 4 vCPUs, 32 GiB of memory and 0 GB of storage. The pricing starts at 0.0563 USD per hour.
4 vCPU
32 GiB Memory
Spare SCore
5,737
(All-cores)
2,865
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
1710004
Name
c3d-highmem-4
Description
4 vCPUs, 32 GB RAM
Family
c3d
Hw Virt
Average Time To Start
16.5
Status
active
Observed At
2026-10-24T12:01:06.410881

Availability

REGION / IDSPOTONDEMAND
Council Bluffs (US) / us-central1
0.0563 USD/h 0.2449 USD/h
The Dalles (US) / us-west1
0.0563 USD/h 0.2449 USD/h
Moncks Corner (US) / us-east1
0.0563 USD/h 0.2449 USD/h
Ashburn (US) / us-east4
0.1102 USD/h 0.2449 USD/h
Mumbai (IN) / asia-south1
0.0733 USD/h 0.2547 USD/h
Stockholm (SE) / europe-north2
0.1338 USD/h 0.2572 USD/h
Eemshaven (NL) / europe-west4
0.1462 USD/h 0.2572 USD/h
Queretaro (MX) / northamerica-south1
0.0593 USD/h 0.267 USD/h
Tel Aviv (IL) / me-west1
0.1186 USD/h 0.2694 USD/h
St. Ghislain (BE) / europe-west1
0.0758 USD/h 0.2697 USD/h
Hamina (FI) / europe-north1
0.1129 USD/h 0.2697 USD/h
Columbus (US) / us-east5
0.1023 USD/h 0.2759 USD/h
London (GB) / europe-west2
0.1423 USD/h 0.2792 USD/h
Changhua County (TW) / asia-east1
0.1014 USD/h 0.2836 USD/h
Frankfurt (DE) / europe-west3
0.1734 USD/h 0.289 USD/h
Jurong West (SG) / asia-southeast1
0.1724 USD/h 0.3022 USD/h
Dammam (SA) / me-central2
0.0663 USD/h 0.3919 USD/h

Processor

vCPUs
4
CPU Allocation
Dedicated
CPU Cores
2
CPU Architecture
x86_64
CPU Manufacturer
AMD
CPU Family
EPYC
CPU Model
9B14
CPU L1D Cache
32 KiB
CPU L1D Cache Total
64 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
64 KiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
2 MiB
CPU L3 Cache
32 MiB
CPU L3 Cache Total
32 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, constant_tsc, rep_good, nopl, nonstop_tsc, cpuid, extd_apicid, tsc_known_freq, pni, pclmulqdq, ssse3, fma, cx16, pcid, sse4_1, sse4_2, x2apic, movbe, popcnt, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, cmp_legacy, cr8_legacy, abm, sse4a, misalignsse, 3dnowprefetch, osvw, topoext, 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, avx512_bf16, clzero, xsaveerptr, wbnoinvd, arat, avx512vbmi, umip, avx512_vbmi2, gfni, vaes, vpclmulqdq, avx512_vnni, avx512_bitalg, avx512_vpopcntdq, rdpid, fsrm
Ecpus
2
Scalability
50

System Resources and Accelerators

MEMORY
Memory Amount
32 GiB
Memory Amount Actual
32 GiB
ACCELERATORS
Accelerator Count
0
Accelerator Memory Min
0 MiB
Accelerator Memory Total
0 MiB
Accelerators
    STORAGE
    Storage Size
    0 GB
    Storages
      NETWORK
      Inbound Traffic
      0 GB/month
      Outbound Traffic
      0 GB/month
      IPv4
      0

      CPU and System Topology

      Server Description

      A memory-optimized virtual machine featuring dedicated AMD EPYC cores and a high RAM-to-vCPU ratio for memory-bound workloads.

      Memory OptimizedGeneral Purpose

      Google Cloud Platform c3d-highmem-4 is a memory-optimized virtual machine featuring 4 vCPUs and 32 GB of RAM, powered by an AMD EPYC 9B14 processor. Built on the x86_64 architecture, it allocates 2 physical cores with hyper-threading and supports AVX-512 and cryptographic instruction sets. The instance lacks local storage and GPU accelerators. Benchmarks indicate strong single-core CPU performance, though multi-core scaling and uncached memory bandwidth are relatively weak. This resource profile makes the instance qualitatively cost-efficient for memory-intensive workloads that do not demand heavy parallel processing, such as small database instances, caching layers, and lightweight text processing.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      0.29Score
      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) 387,381 ops/sec 1,919,289 ops/sec 0.21 50.00% 50.00% -54.00%
      Redis RPS (pipeline=16, SET) 3,003,004 ops/sec 11,728,058 ops/sec 0.25 20.00% 20.00% -24.00%
      PassMark Memory Mark (composite) 2,305 2,416 0.96 10.00% 10.00% -0.41%
      Memory bandwidth (read, 16 MB ~ L3) 15,391 MB/sec 108,466 MB/sec 0.14 10.00% 10.00% -18.00%
      PassMark single-thread CPU 2,684 Mops/s 2,365 Mops/s 1.1 10.00% 10.00% +0.96%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,764

      Geekbench Multi-Core

      Score: 3,748

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 7,014
      Compression
      		 73,139
      Encryption
      		 4,470
      Extended Instructions
      		 4,997
      Floating Point Maths
      		 10,029
      Integer Maths
      		 17,646
      Physics
      		 826
      Prime Numbers
      		 44
      Single Threaded
      		 2,684
      String Sorting
      		 10,713

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2,305
      Database Operations
      		 1,960
      Memory Latency
      		 75
      Memory Read Cached
      		 25,691
      Memory Read Uncached
      		 24,562
      Memory Write
      		 16,377

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 359.74 359.5 1.00×
      bitops
      		 148,032 358,457 2.42×
      branch
      		 197,530 705,094 3.57×
      funccall
      		 573.98 1,627 2.84×
      funcret
      		 19,880 58,457 2.94×
      hash
      		 147,457 442,758 3.00×
      intmath
      		 62,477 164,445 2.63×
      nop
      		 583,833 1,183,810 2.03×
      prime
      		 444,801 1,197,718 2.69×
      rotate
      		 81,830 164,287 2.01×
      str
      		 980,066 2,589,819 2.64×
      wcs
      		 642,288 1,525,884 2.38×
      CryptographySingleMultiScaling
      crypt
      		 3,446 7,493 2.17×
      CompressionSingleMultiScaling
      jpeg
      		 827.29 2,292 2.77×
      zlib
      		 67.79 210.47 3.10×
      HypervisorSingleMultiScaling
      clock
      		 16,524 50,974 3.08×
      clone
      		 270.39 501.73 1.86×
      context
      		 1,729 5,157 2.98×
      cpu-sched
      		 62.52 279.91 4.48×
      eventfd
      		 43,734 218,054 4.99×
      fault
      		 9,900 30,492 3.08×
      fork
      		 4,439 13,434 3.03×
      getrandom
      		 46,894 124,373 2.65×
      hrtimers
      		 237,729 333,196 1.40×
      mprotect
      		 567,445 583,639 1.03×
      mtx
      		 37,944,297 272,141,658 7.17×
      munmap
      		 2,993 9,033 3.02×
      null
      		 182,992 526,466 2.88×
      pipe
      		 934,357 1,321,355 1.41×
      priv-instr
      		 317,921 976,982 3.07×
      resched
      		 504,306 273,988 0.54×
      switch
      		 79,551 570,600 7.17×
      timermix
      		 150,886 455,010 3.02×
      tlb-shootdown
      		 11,944 14,368 1.20×
      tsc
      		 731,301 2,854,787 3.90×
      usersyscall
      		 223,478 690,389 3.09×
      vdso
      		 89,185,658 290,555,280 3.26×
      vfork
      		 32,465 82,174 2.53×
      x86syscall
      		 2,126,393 6,019,462 2.83×
      yield
      		 1,672,931 1,648,682 0.99×
      zero
      		 1,624,152 4,727,164 2.91×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 15,308 32,487 2.12×
      expmath
      		 2,684 8,352 3.11×
      fma
      		 855,466 2,800,592 3.27×
      fp
      		 234.13 723.63 3.09×
      fractal
      		 7 23.6 3.37×
      hyperbolic
      		 3,544 10,573 2.98×
      logmath
      		 4,232 12,089 2.86×
      matrix
      		 4,577 10,750 2.35×
      matrix-3d
      		 627.3 709.25 1.13×
      monte-carlo
      		 106.66 300.24 2.81×
      mpfr
      		 1,560 4,020 2.58×
      powmath
      		 1,263 4,064 3.22×
      trig
      		 1,736 5,303 3.05×
      veccmp
      		 17,652 46,119 2.61×
      vecfp
      		 1,683 5,235 3.11×
      vecmath
      		 3,721 12,017 3.23×
      vecshuf
      		 593.61 1,459 2.46×
      vecwide
      		 26,587 71,065 2.67×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 9.6 21.8 2.27×
      bsearch
      		 284.07 781.16 2.75×
      bubblesort
      		 0.8 2.4 3.00×
      fibsearch
      		 352.89 849.99 2.41×
      heapsort
      		 10.2 27.6 2.71×
      hsearch
      		 9,114 21,008 2.31×
      insertionsort
      		 12 24.6 2.05×
      malloc
      		 2,137,355 8,150,122 3.81×
      mcontend
      		 314.05 831.44 2.65×
      mergesort
      		 31.2 94 3.01×
      qsort
      		 20.2 58.2 2.88×
      skiplist
      		 6,527 21,103 3.23×
      tree
      		 1 2.4 2.40×
      MemorySingleMultiScaling
      cache
      		 633,302 721,418 1.14×
      cachehammer
      		 272,257 993,831 3.65×
      cacheline
      		 42.83 190.9 4.46×
      l1cache
      		 238.71 550.31 2.31×
      memcpy
      		 414.66 854.62 2.06×
      memrate
      		 1.56 2.3 1.47×
      memthrash
      		 54.74 171.51 3.13×
      ptr-chase
      		 9,467,903 32,335,327 3.42×
      spinmem
      		 246.79 211.99 0.86×
      stream
      		 77.97 273.51 3.51×
      vm
      		 59,363 235,691 3.97×

      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
      c3d-highcpu-4 48 GiB0
      c3d-standard-4 416 GiB0
      c3d-highcpu-8 816 GiB0
      c3d-standard-8 832 GiB0
      c3d-standard-8-lssd 832 GiB0
      c3d-highmem-8 864 GiB0
      c3d-highmem-8-lssd 864 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      c3d-highmem-4 FAQs