c3d-highmem-16 by Google Cloud Platform

c3d-highmem-16 is a 16 vCPUs, 128 GB RAM server offered by Google Cloud Platform with 16 vCPUs, 128 GiB of memory and 0 GB of storage. The pricing starts at 0.2367 USD per hour.
16 vCPU
128 GiB Memory
Spare SCore
22,955
(All-cores)
2,865
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
1710016
Name
c3d-highmem-16
Description
16 vCPUs, 128 GB RAM
Family
c3d
Hw Virt
Average Time To Start
16.5
Status
active
Observed At
2026-10-28T20:28:45.635068

Availability

REGION / IDSPOTONDEMAND
Council Bluffs (US) / us-central1
0.2367 USD/h 0.9798 USD/h
The Dalles (US) / us-west1
0.2367 USD/h 0.9798 USD/h
Moncks Corner (US) / us-east1
0.2367 USD/h 0.9798 USD/h
Ashburn (US) / us-east4
0.4628 USD/h 0.9798 USD/h
Mumbai (IN) / asia-south1
0.2787 USD/h 1.019 USD/h
Stockholm (SE) / europe-north2
0.5085 USD/h 1.0287 USD/h
Eemshaven (NL) / europe-west4
0.6172 USD/h 1.0287 USD/h
Queretaro (MX) / northamerica-south1
0.2491 USD/h 1.0679 USD/h
Tel Aviv (IL) / me-west1
0.5218 USD/h 1.0777 USD/h
St. Ghislain (BE) / europe-west1
0.3182 USD/h 1.0788 USD/h
Hamina (FI) / europe-north1
0.4967 USD/h 1.0788 USD/h
Columbus (US) / us-east5
0.3888 USD/h 1.1035 USD/h
London (GB) / europe-west2
0.5406 USD/h 1.1169 USD/h
Changhua County (TW) / asia-east1
0.4463 USD/h 1.1345 USD/h
Frankfurt (DE) / europe-west3
0.6937 USD/h 1.1561 USD/h
Jurong West (SG) / asia-southeast1
0.655 USD/h 1.2087 USD/h
Dammam (SA) / me-central2
0.2787 USD/h 1.5676 USD/h

Processor

vCPUs
16
CPU Allocation
Dedicated
CPU Cores
8
CPU Architecture
x86_64
CPU Manufacturer
AMD
CPU Family
EPYC
CPU Model
9B14
CPU L1D Cache
32 KiB
CPU L1D Cache Total
256 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
256 KiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
8 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
8
Scalability
50

System Resources and Accelerators

MEMORY
Memory Amount
128 GiB
Memory Amount Actual
128 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 processors and high memory density for memory-bound database and caching workloads.

      Memory OptimizedGeneral Purpose

      The Google Cloud Platform c3d-highmem-16 is an x86_64 memory-optimized server powered by an AMD EPYC 9B14 processor. It features 16 dedicated vCPUs across 8 physical cores and 128 GB of RAM, providing a high memory-to-vCPU ratio of 8 GB per core. The processor supports AVX-512 and cryptographic instructions, but the instance lacks local storage and GPU acceleration. Benchmark data shows strong single-core CPU and text processing performance, while multi-core compute, database operations, and small-model LLM inference remain average. A key tradeoff is its memory bandwidth, which drops significantly during large-block uncached read and write operations. This configuration is best suited for memory-intensive workloads such as in-memory databases, caching layers, and text processing tasks that benefit from a high memory-to-compute ratio without requiring local NVMe storage.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      0.81Score
      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) 1,543,818 ops/sec 1,919,289 ops/sec 0.79 50.00% 50.00% -11.00%
      Redis RPS (pipeline=16, SET) 11,461,990 ops/sec 11,728,058 ops/sec 0.92 20.00% 20.00% -1.70%
      PassMark Memory Mark (composite) 2,638 2,416 1.1 10.00% 10.00% +0.96%
      Memory bandwidth (read, 16 MB ~ L3) 42,235 MB/sec 108,466 MB/sec 0.38 10.00% 10.00% -9.20%
      PassMark single-thread CPU 2,692 Mops/s 2,365 Mops/s 1.1 10.00% 10.00% +0.96%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,870

      Geekbench Multi-Core

      Score: 10,058

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 24,416
      Compression
      		 287,838
      Encryption
      		 17,846
      Extended Instructions
      		 20,413
      Floating Point Maths
      		 40,243
      Integer Maths
      		 70,734
      Physics
      		 2,223
      Prime Numbers
      		 121
      Single Threaded
      		 2,692
      String Sorting
      		 39,145

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2,638
      Database Operations
      		 7,093
      Memory Latency
      		 70
      Memory Read Cached
      		 25,808
      Memory Read Uncached
      		 24,896
      Memory Write
      		 18,534

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 527.23 302.14 0.57×
      bitops
      		 148,048 1,437,740 9.71×
      branch
      		 197,237 2,829,070 14.34×
      funccall
      		 573.75 6,344 11.06×
      funcret
      		 19,829 227,638 11.48×
      hash
      		 147,385 1,775,843 12.05×
      intmath
      		 62,259 669,959 10.76×
      nop
      		 583,975 4,742,223 8.12×
      prime
      		 464,619 4,767,241 10.26×
      rotate
      		 81,967 658,128 8.03×
      str
      		 1,010,217 10,181,768 10.08×
      wcs
      		 645,466 5,971,785 9.25×
      CryptographySingleMultiScaling
      crypt
      		 3,484 30,156 8.66×
      CompressionSingleMultiScaling
      jpeg
      		 841.26 9,156 10.88×
      zlib
      		 55.16 828.61 15.02×
      HypervisorSingleMultiScaling
      clock
      		 16,475 178,389 10.83×
      clone
      		 303.33 1,998 6.59×
      context
      		 1,725 20,653 11.97×
      cpu-sched
      		 70.66 1,024 14.49×
      eventfd
      		 46,084 473,579 10.28×
      fault
      		 10,253 120,497 11.75×
      fork
      		 4,515 43,966 9.74×
      getrandom
      		 46,915 498,295 10.62×
      hrtimers
      		 568,052 1,457,974 2.57×
      mprotect
      		 1,242,565 2,380,559 1.92×
      mtx
      		 40,992,795 961,558,756 23.46×
      munmap
      		 2,990 30,777 10.29×
      null
      		 182,731 2,107,511 11.53×
      pipe
      		 936,738 5,393,744 5.76×
      priv-instr
      		 327,539 3,953,715 12.07×
      resched
      		 2,824,311 533,001 0.19×
      switch
      		 83,296 2,287,678 27.46×
      timermix
      		 151,706 1,839,168 12.12×
      tlb-shootdown
      		 15,217 51,070 3.36×
      tsc
      		 730,070 11,437,637 15.67×
      usersyscall
      		 227,601 2,757,636 12.12×
      vdso
      		 89,125,386 1,166,371,304 13.09×
      vfork
      		 34,210 253,563 7.41×
      x86syscall
      		 2,122,511 24,105,074 11.36×
      yield
      		 7,191,436 7,399,326 1.03×
      zero
      		 1,619,378 18,955,000 11.71×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 15,265 130,011 8.52×
      expmath
      		 2,700 34,009 12.60×
      fma
      		 854,501 11,239,808 13.15×
      fp
      		 233.78 2,870 12.27×
      fractal
      		 7 94.01 13.43×
      hyperbolic
      		 3,541 42,406 11.97×
      logmath
      		 4,235 48,618 11.48×
      matrix
      		 4,574 43,178 9.44×
      matrix-3d
      		 251.5 1,197 4.76×
      monte-carlo
      		 106.67 1,201 11.26×
      mpfr
      		 1,562 16,027 10.26×
      powmath
      		 1,256 16,296 12.98×
      trig
      		 1,738 21,280 12.24×
      veccmp
      		 17,679 184,986 10.46×
      vecfp
      		 1,680 19,546 11.63×
      vecmath
      		 3,722 48,219 12.96×
      vecshuf
      		 592.52 5,863 9.90×
      vecwide
      		 26,540 285,425 10.75×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 9.6 86.8 9.04×
      bsearch
      		 284.43 3,180 11.18×
      bubblesort
      		 0.8 9.6 12.00×
      fibsearch
      		 349.7 3,466 9.91×
      heapsort
      		 10 112 11.20×
      hsearch
      		 9,495 85,652 9.02×
      insertionsort
      		 11.8 96.6 8.19×
      malloc
      		 3,595,965 37,121,353 10.32×
      mcontend
      		 231.49 3,178 13.73×
      mergesort
      		 31.2 375.59 12.04×
      qsort
      		 20.4 233.39 11.44×
      skiplist
      		 6,486 84,806 13.08×
      tree
      		 1.8 12.79 7.11×
      MemorySingleMultiScaling
      cache
      		 822,690 2,123,421 2.58×
      cachehammer
      		 267,030 3,839,823 14.38×
      cacheline
      		 83.37 1,210 14.51×
      l1cache
      		 249.15 2,173 8.72×
      memcpy
      		 416.39 3,417 8.21×
      memrate
      		 2.72 3.06 1.13×
      memthrash
      		 180.01 358.73 1.99×
      ptr-chase
      		 39,879,555 125,228,866 3.14×
      spinmem
      		 252.99 789.66 3.12×
      stream
      		 113.48 2,097 18.48×
      vm
      		 58,948 292,844 4.97×

      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-highmem-4 432 GiB0
      c3d-highcpu-8 816 GiB0
      c3d-standard-8 832 GiB0
      c3d-standard-8-lssd 832 GiB0
      c3d-highmem-8 864 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      c3d-highmem-16 FAQs