h4d-standard-192 by Google Cloud Platform

h4d-standard-192 is a 192 vCPUs, 744 GB RAM server offered by Google Cloud Platform with 192 vCPUs, 720 GiB of memory and 0 GB of storage. The pricing starts at 2.736 USD per hour.
192 vCPU
720 GiB Memory
Spare SCore
655,072
(All-cores)
3,461
(Single-core)

Specifications

Server Metadata

Vendor ID
gcp
Server ID
999904050
Name
h4d-standard-192
Description
192 vCPUs, 744 GB RAM
Family
h4d
Hw Virt
Average Time To Start
31
Status
active
Observed At
2026-11-01T21:21:17.321490

Availability

REGION / IDSPOTONDEMAND
Council Bluffs (US) / us-central1
3.6374 USD/h 7.8538 USD/h
Moncks Corner (US) / us-east1
3.6374 USD/h 7.8538 USD/h
Eemshaven (NL) / europe-west4
2.736 USD/h 8.4035 USD/h
Jurong West (SG) / asia-southeast1
3.1608 USD/h 10.2097 USD/h
Mumbai (IN) / asia-south1
2.7497 USD/h 10.9953 USD/h

Processor

vCPUs
192
CPU Allocation
Dedicated
CPU Cores
192
CPU Architecture
x86_64
CPU Manufacturer
AMD
CPU Family
EPYC
CPU Model
9B45
CPU L1D Cache
48 KiB
CPU L1D Cache Total
9 MiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
6 MiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
192 MiB
CPU L3 Cache
32 MiB
CPU L3 Cache Total
768 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, xtopology, nonstop_tsc, cpuid, extd_apicid, tsc_known_freq, pni, pclmulqdq, monitor, 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, mwaitx, ssbd, ibrs, ibpb, stibp, ibrs_enhanced, 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, rdpid, movdiri, movdir64b, avx512_vp2intersect, flush_l1d
Ecpus
189.3
Scalability
98.59

System Resources and Accelerators

MEMORY
Memory Amount
720 GiB
Memory Amount Actual
720 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 dedicated 192-core AMD EPYC server with high memory bandwidth, optimized for massive parallel processing and high-throughput database workloads.

      General PurposeCompute Optimized

      Google Cloud Platform h4d-standard-192 is an x86_64 server from the h4d family, featuring 192 dedicated physical AMD EPYC 9B45 cores with a 1.0 thread-per-core configuration and 720.0 GB of RAM. Lacking local storage and GPU accelerators, this instance relies on external storage and is optimized for pure CPU-bound execution. Benchmark results place the server in the top 10% tier, highlighted by a stress-ng multi-core score of 655,072.06, a Redis SET performance of 495.56 million operations per second, and a static web serving throughput of 187.5 GB/sec. Memory read bandwidth reaches 1,054.65 GB/sec for large blocks. This configuration is highly efficient for large-scale database operations, high-throughput web serving, and parallelized CPU-bound workloads.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      15Score
      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) 55,368,606 ops/sec 1,918,343 ops/sec 29 50.00% 50.00% +440.00%
      Redis RPS (pipeline=16, SET) 358,879,158 ops/sec 11,704,734 ops/sec 30 20.00% 20.00% +97.00%
      PassMark Memory Mark (composite) 3,134 2,416 1.3 10.00% 10.00% +2.70%
      Memory bandwidth (read, 16 MB ~ L3) 1,291,867 MB/sec 108,466 MB/sec 12 10.00% 10.00% +28.00%
      PassMark single-thread CPU 3,470 Mops/s 2,365 Mops/s 1.5 10.00% 10.00% +4.10%

      Memory Bandwidth

      Compression

      OpenSSL

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 175,336
      Compression
      		 5,186,485
      Encryption
      		 274,651
      Extended Instructions
      		 441,027
      Floating Point Maths
      		 1,313,816
      Integer Maths
      		 1,332,769
      Physics
      		 61,420
      Prime Numbers
      		 4,299
      Single Threaded
      		 3,470
      String Sorting
      		 671,666

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 3,134
      Database Operations
      		 45,604
      Memory Latency
      		 73
      Memory Read Cached
      		 31,086
      Memory Read Uncached
      		 30,795
      Memory Write
      		 31,080

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 486.04 297.6 0.61×
      bitops
      		 211,997 38,985,935 183.90×
      branch
      		 169,037 31,198,932 184.57×
      funccall
      		 831.74 147,502 177.34×
      funcret
      		 24,639 4,362,730 177.07×
      hash
      		 199,172 37,611,979 188.84×
      intmath
      		 73,631 13,859,683 188.23×
      nop
      		 394,168 74,337,360 188.59×
      prime
      		 574,954 96,425,393 167.71×
      rotate
      		 130,770 24,670,781 188.66×
      str
      		 1,509,168 235,927,483 156.33×
      wcs
      		 997,001 150,583,100 151.04×
      CryptographySingleMultiScaling
      crypt
      		 5,003 841,864 168.29×
      CompressionSingleMultiScaling
      jpeg
      		 1,189 173,333 145.82×
      zlib
      		 98.19 12,491 127.21×
      HypervisorSingleMultiScaling
      clock
      		 39,789 217,476 5.47×
      clone
      		 355.15 12,093 34.05×
      context
      		 8,638 1,615,296 187.00×
      cpu-sched
      		 67.51 12,143 179.87×
      eventfd
      		 141,454 10,913,955 77.16×
      fault
      		 42,635 189,864 4.45×
      fork
      		 6,073 68,691 11.31×
      getrandom
      		 90,395 15,790,143 174.68×
      hrtimers
      		 592,900 4,462,751 7.53×
      mprotect
      		 476,805 35,986,415 75.47×
      mtx
      		 33,049,459 12,247,568,701 370.58×
      munmap
      		 4,600 65,033 14.14×
      null
      		 1,427,031 259,329,232 181.73×
      pipe
      		 2,607,125 101,288,086 38.85×
      priv-instr
      		 1,311,625 20,563,954 15.68×
      resched
      		 5,960,031 67,956,150 11.40×
      switch
      		 394,225 108,931,456 276.32×
      timermix
      		 511,851 95,574,338 186.72×
      tlb-shootdown
      		 13,972 521,120 37.30×
      tsc
      		 812,086 154,422,243 190.16×
      usersyscall
      		 1,038,796 20,297,262 19.54×
      vdso
      		 99,585,208 18,698,302,120 187.76×
      vfork
      		 36,295 152,789 4.21×
      x86syscall
      		 18,247,040 3,341,630,675 183.13×
      yield
      		 449,875,446 402,831,986 0.90×
      zero
      		 7,234,051 1,319,255,937 182.37×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 16,102 2,845,583 176.72×
      expmath
      		 3,683 650,188 176.56×
      fma
      		 1,442,089 255,087,227 176.89×
      fp
      		 201.29 35,304 175.39×
      fractal
      		 8.2 1,485 181.10×
      hyperbolic
      		 4,994 917,997 183.81×
      logmath
      		 5,239 980,592 187.19×
      matrix
      		 8,229 1,304,504 158.53×
      matrix-3d
      		 1,401 36,753 26.24×
      monte-carlo
      		 430.33 74,380 172.85×
      mpfr
      		 2,215 376,732 170.05×
      powmath
      		 1,690 317,197 187.66×
      trig
      		 2,242 397,902 177.51×
      veccmp
      		 27,671 4,756,835 171.91×
      vecfp
      		 2,251 397,568 176.64×
      vecmath
      		 4,349 814,462 187.27×
      vecshuf
      		 922.02 160,606 174.19×
      vecwide
      		 37,056 6,052,278 163.33×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 12 2,047 170.58×
      bsearch
      		 336.12 57,540 171.19×
      bubblesort
      		 1 185.4 185.40×
      fibsearch
      		 396.76 71,287 179.67×
      heapsort
      		 13.2 2,190 165.89×
      hsearch
      		 12,385 1,998,044 161.32×
      insertionsort
      		 7.8 1,747 224.00×
      malloc
      		 5,096,129 260,078,101 51.03×
      mcontend
      		 70.5 25,358 359.69×
      mergesort
      		 36.2 5,972 164.97×
      qsort
      		 24.8 4,160 167.74×
      skiplist
      		 7,780 1,365,231 175.48×
      tree
      		 2.4 306.69 127.79×
      MemorySingleMultiScaling
      cache
      		 849,959 3,143,398 3.70×
      cachehammer
      		 291,756 13,387,315 45.89×
      cacheline
      		 46.97 5,461 116.27×
      l1cache
      		 1,260 195,465 155.16×
      memcpy
      		 736.82 132,039 179.20×
      memrate
      		 0.99 70.34 71.05×
      memthrash
      		 509.98 1,686 3.31×
      ptr-chase
      		 73,667,883 2,004,390,288 27.21×
      spinmem
      		 318.59 14,240 44.70×
      stream
      		 77.1 337,754 4380.72×
      vm
      		 238,756 617,282 2.59×

      Stress-ng Raw Scores

      Stress-ng Relative Multicore Performance

      Static Web Server

      Redis

      PostgreSQL heavy read-only throughput

      Alternatives

      Servers of the Same Family

      INSTANCEvCPUsMEMORYAccelerators
      h4d-highmem-192 1921488 GiB0
      h4d-highmem-192-lssd 1921488 GiB0
      h4d-megamem-192-lssd 1923024 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      h4d-standard-192 FAQs