c3-highmem-44 by Google Cloud Platform

c3-highmem-44 is a 44 vCPUs, 352 GB RAM server offered by Google Cloud Platform with 44 vCPUs, 352 GiB of memory and 0 GB of storage. The pricing starts at 0.304 USD per hour.
44 vCPU
352 GiB Memory
Spare SCore
36,647
(All-cores)
1,623
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
1330044
Name
c3-highmem-44
Description
44 vCPUs, 352 GB RAM
Family
c3
Hw Virt
Average Time To Start
26
Status
active
Observed At
2026-10-25T13:42:08.772686

Availability

REGION / IDSPOTONDEMAND
Ashburn (US) / us-east4
0.7365 USD/h 2.9108 USD/h
Columbus (US) / us-east5
1.0314 USD/h 2.9108 USD/h
Council Bluffs (US) / us-central1
1.0908 USD/h 2.9108 USD/h
The Dalles (US) / us-west1
1.0908 USD/h 2.9108 USD/h
Moncks Corner (US) / us-east1
1.0908 USD/h 2.9108 USD/h
Mumbai (IN) / asia-south1
0.4966 USD/h 3.0272 USD/h
Delhi (IN) / asia-south2
0.304 USD/h 3.0273 USD/h
Eemshaven (NL) / europe-west4
1.7734 USD/h 3.0563 USD/h
Toronto (CA) / northamerica-northeast2
0.4639 USD/h 3.2051 USD/h
Montréal (CA) / northamerica-northeast1
0.8335 USD/h 3.2051 USD/h
St. Ghislain (BE) / europe-west1
1.3325 USD/h 3.2051 USD/h
Las Vegas (US) / us-west4
1.5498 USD/h 3.2784 USD/h
London (GB) / europe-west2
1.9911 USD/h 3.3183 USD/h
Changhua County (TW) / asia-east1
0.9291 USD/h 3.3704 USD/h
Berlin (DE) / europe-west10
0.5844 USD/h 3.4346 USD/h
Dallas (US) / us-south1
0.3091 USD/h 3.4347 USD/h
Frankfurt (DE) / europe-west3
1.3255 USD/h 3.4347 USD/h
Los Angeles (US) / us-west2
1.4211 USD/h 3.499 USD/h
Salt Lake City (US) / us-west3
2.0992 USD/h 3.499 USD/h
Doha (QA) / me-central1
0.3185 USD/h 3.5366 USD/h
Jurong West (SG) / asia-southeast1
1.8271 USD/h 3.591 USD/h
Tokyo (JP) / asia-northeast1
1.7587 USD/h 3.738 USD/h
Jakarta (ID) / asia-southeast2
0.4101 USD/h 3.9141 USD/h
Osasco (BR) / southamerica-east1
0.4588 USD/h 4.622 USD/h
Dammam (SA) / me-central2
0.8362 USD/h 4.6572 USD/h

Processor

vCPUs
44
CPU Allocation
Dedicated
CPU Cores
22
CPU Speed
2.7 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU Model
8481C
CPU L1D Cache
48 KiB
CPU L1D Cache Total
1 MiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
704 KiB
CPU L2 Cache
2 MiB
CPU L2 Cache Total
44 MiB
CPU L3 Cache
105 MiB
CPU L3 Cache Total
105 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, ss, ht, syscall, nx, pdpe1gb, rdtscp, lm, constant_tsc, rep_good, nopl, xtopology, nonstop_tsc, cpuid, tsc_known_freq, pni, pclmulqdq, ssse3, fma, cx16, pcid, sse4_1, sse4_2, x2apic, movbe, popcnt, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, abm, 3dnowprefetch, ssbd, ibrs, ibpb, stibp, ibrs_enhanced, fsgsbase, tsc_adjust, bmi1, avx2, smep, bmi2, erms, invpcid, rtm, avx512f, avx512dq, rdseed, adx, smap, avx512ifma, clflushopt, clwb, avx512cd, sha_ni, avx512bw, avx512vl, xsaveopt, xsavec, xgetbv1, xsaves, avx_vnni, avx512_bf16, arat, avx512vbmi, umip, avx512_vbmi2, gfni, vaes, vpclmulqdq, avx512_vnni, avx512_bitalg, avx512_vpopcntdq, la57, rdpid, cldemote, movdiri, movdir64b, fsrm, md_clear, serialize, amx_bf16, avx512_fp16, amx_tile, amx_int8, arch_capabilities
Ecpus
22.6
Scalability
51.36

System Resources and Accelerators

MEMORY
Memory Amount
352 GiB
Memory Amount Actual
352 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 x86_64 server featuring high memory density and Intel AMX support for memory-bound enterprise workloads without local storage.

      Memory OptimizedGeneral Purpose

      Google Cloud Platform c3-highmem-44 is a memory-optimized server configured with 44 vCPUs and 352 GB of RAM, yielding an 8.0 GB RAM-to-vCPU ratio. It runs on an Intel Xeon 8481C x86_64 processor with 22 physical cores, a 2.7 GHz clock speed, and a 105 MB L3 cache. The hardware supports Intel AMX and AVX-512 instruction sets but lacks local storage and GPU accelerators. Benchmarks show average multi-core performance alongside strong capabilities in image processing, encryption, and small-model LLM prompt processing. However, text generation for large 70B models is poor. This instance is qualitatively cost-efficient for memory-heavy applications that do not require local NVMe storage or GPU acceleration, making it suitable for database operations, software compilation, and memory-bound enterprise workloads.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      2.4Score
      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) 7,161,084 ops/sec 1,919,289 ops/sec 3.8 50.00% 50.00% +95.00%
      Redis RPS (pipeline=16, SET) 32,581,405 ops/sec 11,728,058 ops/sec 2.8 20.00% 20.00% +23.00%
      PassMark Memory Mark (composite) 2,234 2,416 0.92 10.00% 10.00% -0.83%
      Memory bandwidth (read, 16 MB ~ L3) 120,510 MB/sec 108,466 MB/sec 1.1 10.00% 10.00% +0.96%
      PassMark single-thread CPU 2,480 Mops/s 2,365 Mops/s 1 10.00% 10.00% 0.00%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,725

      Geekbench Multi-Core

      Score: 15,596

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 47,634
      Compression
      		 645,957
      Encryption
      		 38,871
      Extended Instructions
      		 46,007
      Floating Point Maths
      		 124,936
      Integer Maths
      		 175,262
      Physics
      		 3,488
      Prime Numbers
      		 250
      Single Threaded
      		 2,480
      String Sorting
      		 85,063

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2,234
      Database Operations
      		 18,840
      Memory Latency
      		 69
      Memory Read Cached
      		 22,444
      Memory Read Uncached
      		 9,570
      Memory Write
      		 8,393

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 220.24 163.46 0.74×
      bitops
      		 124,414 3,303,995 26.56×
      branch
      		 116,021 3,966,609 34.19×
      funccall
      		 626.12 17,665 28.21×
      funcret
      		 10,481 362,761 34.61×
      hash
      		 148,526 4,776,086 32.16×
      intmath
      		 54,328 1,424,076 26.21×
      nop
      		 224,242 4,030,324 17.97×
      prime
      		 400,749 10,385,566 25.92×
      rotate
      		 83,768 1,956,977 23.36×
      str
      		 757,074 25,240,342 33.34×
      wcs
      		 576,940 15,480,653 26.83×
      CryptographySingleMultiScaling
      crypt
      		 2,839 59,622 21.00×
      CompressionSingleMultiScaling
      jpeg
      		 704.29 19,367 27.50×
      zlib
      		 45.71 1,811 39.62×
      HypervisorSingleMultiScaling
      clock
      		 37,065 440,994 11.90×
      clone
      		 471.51 5,296 11.23×
      context
      		 4,381 159,001 36.29×
      cpu-sched
      		 67.83 2,826 41.66×
      eventfd
      		 56,647 1,446,959 25.54×
      fault
      		 25,273 304,455 12.05×
      fork
      		 5,539 104,443 18.86×
      getrandom
      		 49,773 1,591,782 31.98×
      hrtimers
      		 276,956 5,129,645 18.52×
      mprotect
      		 1,135,688 12,124,694 10.68×
      mtx
      		 12,038,355 1,285,016,514 106.74×
      munmap
      		 4,298 87,894 20.45×
      null
      		 750,086 26,053,581 34.73×
      pipe
      		 664,253 29,633,591 44.61×
      priv-instr
      		 699,278 14,068,862 20.12×
      resched
      		 14,934,413 2,835,234 0.19×
      switch
      		 79,380 11,587,750 145.98×
      timermix
      		 200,949 7,150,920 35.59×
      tlb-shootdown
      		 9,729 77,115 7.93×
      tsc
      		 488,469 18,003,829 36.86×
      usersyscall
      		 598,582 13,632,512 22.77×
      vdso
      		 75,768,225 2,583,984,888 34.10×
      vfork
      		 33,998 270,995 7.97×
      x86syscall
      		 8,387,006 309,743,915 36.93×
      yield
      		 34,352,166 44,377,787 1.29×
      zero
      		 5,398,734 188,396,312 34.90×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 13,595 386,230 28.41×
      expmath
      		 2,611 89,014 34.09×
      fma
      		 1,159,866 35,896,099 30.95×
      fp
      		 259.15 8,865 34.21×
      fractal
      		 5.8 186.05 32.08×
      hyperbolic
      		 2,810 99,184 35.30×
      logmath
      		 4,372 151,946 34.76×
      matrix
      		 5,106 127,223 24.92×
      matrix-3d
      		 659.32 3,736 5.67×
      monte-carlo
      		 247.01 8,880 35.95×
      mpfr
      		 1,455 35,715 24.54×
      powmath
      		 1,547 53,213 34.40×
      trig
      		 2,185 63,689 29.14×
      veccmp
      		 20,728 525,985 25.38×
      vecfp
      		 1,838 46,757 25.43×
      vecmath
      		 3,234 102,743 31.77×
      vecshuf
      		 3,224 132,832 41.21×
      vecwide
      		 63,609 1,864,478 29.31×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 7.4 193.79 26.19×
      bsearch
      		 237.21 6,702 28.25×
      bubblesort
      		 0.8 26.4 33.00×
      fibsearch
      		 262.4 6,832 26.03×
      heapsort
      		 8.4 246.99 29.40×
      hsearch
      		 7,106 187,405 26.37×
      insertionsort
      		 10.2 209.8 20.57×
      malloc
      		 2,567,264 58,745,707 22.88×
      mcontend
      		 109.67 7,532 68.68×
      mergesort
      		 25.8 811.18 31.44×
      qsort
      		 18.4 565.59 30.74×
      skiplist
      		 4,564 158,991 34.83×
      tree
      		 1.4 26.37 18.84×
      MemorySingleMultiScaling
      cache
      		 285,352 1,244,111 4.36×
      cachehammer
      		 220,340 6,800,786 30.86×
      cacheline
      		 46.55 3,528 75.79×
      l1cache
      		 920.91 7,684 8.34×
      memcpy
      		 371.58 7,444 20.03×
      memrate
      		 0.17 6.57 38.65×
      memthrash
      		 240.55 883.79 3.67×
      ptr-chase
      		 29,077,156 352,631,298 12.13×
      spinmem
      		 209.79 1,863 8.88×
      stream
      		 14.75 4,340 294.23×
      vm
      		 96,293 298,124 3.10×

      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
      c3-highcpu-4 48 GiB0
      c3-standard-4 416 GiB0
      c3-standard-4-lssd 416 GiB0
      c3-highmem-4 432 GiB0
      c3-highcpu-8 816 GiB0
      c3-standard-8 832 GiB0
      c3-standard-8-lssd 832 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      c3-highmem-44 FAQs