c8g.24xlarge by Amazon Web Services

c8g.24xlarge is a Compute optimized [AWS Graviton processors] Gen8 24xlarge server offered by Amazon Web Services with 96 vCPUs, 192 GiB of memory and 0 GB of storage. The pricing starts at 0.2878 USD per hour.
96 vCPU
192 GiB Memory
Spare SCore
163,524
(All-cores)
1,706
(Single-core)

Specifications #

Server Metadata #

Vendor ID
aws
Name
c8g.24xlarge
Description
Compute optimized [AWS Graviton processors] Gen8 24xlarge
Family
Compute Optimized
Series
c8g
Hw Virt
Average Time To Start
7.67
Status
active
Observed At
2026-11-21T21:06:12.485600

Availability #

Region / IDSpotOndemand
Hyderabad (IN) / ap-south-2
0.290267 USD/h
2.591 USD/h
Mumbai (IN) / ap-south-1
0.866933 USD/h
2.591 USD/h
(MY) / ap-southeast-5
0.9826 USD/h
3.7382 USD/h
(TH) / ap-southeast-7
1.012167 USD/h
3.7382 USD/h
Ohio (US) / us-east-2
1.0568 USD/h
3.815 USD/h
Northern Virgina (US) / us-east-1
1.3743 USD/h
3.8285 USD/h
Oregon (US) / us-west-2
1.314275 USD/h
3.8285 USD/h
Stockholm (SE) / eu-north-1
0.9638 USD/h
4.0848 USD/h
Aragón (ES) / eu-south-2
0.862433 USD/h
4.0925 USD/h
Dublin (IE) / eu-west-1
1.8882 USD/h
4.0934 USD/h
Calgary (CA) / ca-west-1
0.6859 USD/h
4.1741 USD/h
Quebec (CA) / ca-central-1
0.933467 USD/h
4.1741 USD/h
Tel Aviv (IL) / il-central-1
1.832267 USD/h
4.2979 USD/h
Seoul (KR) / ap-northeast-2
0.9049 USD/h
4.3085 USD/h
Taipei (TW) / ap-east-2
1.42785 USD/h
4.3219 USD/h
Frankfurt (DE) / eu-central-1
1.3554 USD/h
4.3536 USD/h
Jakarta (ID) / ap-southeast-3
0.454167 USD/h
4.3982 USD/h
Singapore (SG) / ap-southeast-1
1.591367 USD/h
4.3987 USD/h
Milan (IT) / eu-south-1
0.763867 USD/h
4.5226 USD/h
Paris (FR) / eu-west-3
0.887867 USD/h
4.5331 USD/h
London (GB) / eu-west-2
1.3022 USD/h
4.5331 USD/h
California (US) / us-west-1
1.2003 USD/h
4.7578 USD/h
Zurich (CH) / eu-central-2
0.8092 USD/h
4.7894 USD/h
Osaka (JP) / ap-northeast-3
1.185767 USD/h
4.8019 USD/h
Tokyo (JP) / ap-northeast-1
1.566333 USD/h
4.8029 USD/h
Hong Kong (HK) / ap-east-1
0.702967 USD/h
4.8048 USD/h
Melbourne (AU) / ap-southeast-4
0.535633 USD/h
4.9814 USD/h
Sydney (AU) / ap-southeast-2
1.2803 USD/h
4.9824 USD/h
Cape Town (ZA) / af-south-1
1.1095 USD/h
5.1168 USD/h
(NZ) / ap-southeast-6
0.558033 USD/h
5.231 USD/h
Sao Paulo (BR) / sa-east-1
1.556733 USD/h
5.8646 USD/h

Processor #

vCPUs
96
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
96
CPU Speed
2.8 GHz
CPU Architecture
arm64
CPU Manufacturer
AWS
CPU Family
ARMv9
CPU Model
Neoverse-V2
CPU L1D Cache
64 KiB
CPU L1D Cache Total
6 MiB
CPU L1I Cache
64 KiB
CPU L1I Cache Total
6 MiB
CPU L2 Cache
2 MiB
CPU L2 Cache Total
192 MiB
CPU L3 Cache
36 MiB
CPU L3 Cache Total
36 MiB
CPU Flags
fp, asimd, evtstrm, aes, pmull, sha1, sha2, crc32, atomics, fphp, asimdhp, cpuid, asimdrdm, jscvt, fcma, lrcpc, dcpop, sha3, asimddp, sha512, sve, asimdfhm, dit, uscat, ilrcpc, flagm, ssbs, sb, paca, pacg, dcpodp, sve2, sveaes, svepmull, svebitperm, svesha3, flagm2, frint, svei8mm, svebf16, i8mm, bf16, dgh, rng, bti
Ecpus
95.8
Scalability
99.79

System Resources and Accelerators #

Memory
Memory Amount
192 GiB
Memory Amount Actual
189 GiB
Accelerators
Accelerator Count
0
Accelerator Memory Min
0 MiB
Accelerator Memory Total
0 MiB
Accelerators
    Storage
    Storage Size
    0 GB
    Storages
      Compatible Storage IDs
      standard, gp2, gp3, st1, sc1, io1, io2
      Network
      Network Speed Baseline
      40 Gbps
      Network Speed Max
      40 Gbps
      Network Storage Speed Baseline
      30 Gbps
      Network Storage Speed Max
      30 Gbps
      Inbound Traffic
      0 GB/month
      Outbound Traffic
      0 GB/month
      IPv4
      0

      CPU and System Topology #

      Server Description #

      Dedicated 96-core ARMv9 computing delivering high parallel processing throughput and memory bandwidth for compute-focused infrastructure workloads.

      Amazon Web Services c8g.24xlarge is a compute-optimized server powered by 96 dedicated ARMv9 Neoverse-V2 cores at 2.8 GHz and 192.0 GB of memory on the AWS Nitro System. Featuring a 1:2 memory-to-core ratio, it does not include local storage or hardware GPUs, depending instead on network storage and a 40 Gbps baseline network interface. While single-thread benchmarks place in the average tier, full-core utilization demonstrates top-tier multi-threaded processing, reflected in high Geekbench multi-core scores, fast Clang compilation, and extensive uncached memory bandwidth. Its compute density yields strong operational value for parallel processing, making it appropriate for large-scale software builds, batch data processing, distributed container workloads, and high-throughput web caching.

      Economics #

      Average Price per Region #

      Prices per Zone #

      Lowest Prices #

      Performance #

      Workload Profiles #

      6.5Score
      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) 22,285,003 ops/sec 1,921,522 ops/sec 12 50.00% 50.00% +250.00%
      Redis RPS (pipeline=16, SET) 119,818,126 ops/sec 11,803,344 ops/sec 10 20.00% 20.00% +58.00%
      PassMark Memory Mark (composite) 3,377 2,407 1.4 10.00% 10.00% +3.40%
      Memory bandwidth (read, 16 MB ~ L3) 546,767 MB/sec 108,674 MB/sec 5 10.00% 10.00% +17.00%
      PassMark single-thread CPU 1,944 Mops/s 2,365 Mops/s 0.79 10.00% 10.00% -2.30%

      Memory Bandwidth#

      Compression #

      OpenSSL #

      Geekbench Single-Core #

      Score: 1,891

      Geekbench Multi-Core #

      Score: 25,987

      Passmark CPU Scores #

      BENCHMARKSCORE
      Mark
      56,635
      Compression
      637,585
      Encryption
      18,127
      Extended Instructions
      80,373
      Floating Point Maths
      581,289
      Integer Maths
      500,192
      Physics
      18,068
      Prime Numbers
      793
      Single Threaded
      1,944
      String Sorting
      416,453

      Passmark Memory Scores #

      BENCHMARKSCORE
      Memory Mark
      3,377
      Database Operations
      46,998
      Memory Latency
      47
      Memory Read Cached
      21,176
      Memory Read Uncached
      19,806
      Memory Write
      21,153

      Stress-ng Stressors #

      CPU integerSingleMultiScaling
      atomic
      156.26 - -
      bitops
      144,792 13,869,976 95.79×
      branch
      227,033 21,764,867 95.87×
      funccall
      1,971 188,899 95.83×
      funcret
      34,314 2,680,457 78.12×
      hash
      155,602 14,915,677 95.86×
      intmath
      32,777 3,138,470 95.75×
      nop
      455,102 43,656,128 95.93×
      prime
      499,186 47,931,440 96.02×
      rotate
      134,186 12,849,643 95.76×
      str
      752,276 68,272,128 90.75×
      wcs
      201,626 19,419,173 96.31×
      CryptographySingleMultiScaling
      crypt
      3,465 337,602 97.44×
      CompressionSingleMultiScaling
      jpeg
      740.52 55,081 74.38×
      zlib
      46.87 3,870 82.57×
      HypervisorSingleMultiScaling
      clock
      42,609 251,829 5.91×
      clone
      368.61 16,416 44.54×
      context
      3,424 329,748 96.31×
      cpu-sched
      61.47 6,134 99.79×
      eventfd
      103,881 3,153,161 30.35×
      fault
      24,201 376,412 15.55×
      fork
      5,430 77,669 14.30×
      getrandom
      62,235 5,966,526 95.87×
      hrtimers
      777,603 12,914,164 16.61×
      mprotect
      1,263,502 22,135,415 17.52×
      mtx
      8,554,874 4,455,271,648 520.79×
      munmap
      3,863 104,122 26.96×
      null
      593,075 57,785,935 97.43×
      pipe
      1,170,024 49,730,774 42.50×
      priv-instr
      900,024 12,898,837 14.33×
      resched
      2,858,343 8,652,846 3.03×
      switch
      145,165 51,830,714 357.05×
      timermix
      573,166 54,671,284 95.38×
      tlb-shootdown
      17,027 283,291 16.64×
      vdso
      44,970,016 4,241,697,083 94.32×
      vfork
      35,676 253,359 7.10×
      yield
      126,918,089 132,763,962 1.05×
      zero
      2,797,429 269,022,378 96.17×
      CPU float/SIMDSingleMultiScaling
      eigen
      1,936 185,447 95.79×
      expmath
      366.62 35,145 95.86×
      fma
      775,521 65,552,139 84.53×
      fp
      151.2 14,680 97.09×
      fractal
      7.8 734.29 94.14×
      hyperbolic
      354.13 33,936 95.83×
      logmath
      429.5 41,157 95.83×
      matrix
      6,601 631,513 95.66×
      matrix-3d
      1,341 22,646 16.89×
      monte-carlo
      237.07 22,964 96.86×
      mpfr
      1,438 137,865 95.87×
      powmath
      248.95 23,860 95.84×
      trig
      475.83 45,650 95.94×
      veccmp
      21,813 2,091,130 95.87×
      vecfp
      1,241 111,060 89.50×
      vecmath
      4,444 426,003 95.86×
      vecshuf
      882.67 84,733 96.00×
      vecwide
      27,005 2,206,874 81.72×
      AlgorithmsSingleMultiScaling
      bitonicsort
      9 863.58 95.95×
      bsearch
      341.9 32,731 95.73×
      bubblesort
      1.2 115.2 96.00×
      fibsearch
      365.3 34,958 95.70×
      heapsort
      13 1,248 95.98×
      hsearch
      8,456 810,669 95.87×
      insertionsort
      6.8 641 94.26×
      malloc
      3,944,310 198,918,749 50.43×
      mcontend
      259.92 196,458 755.84×
      mergesort
      33.4 3,204 95.91×
      qsort
      22.2 2,131 95.99×
      skiplist
      6,742 645,988 95.82×
      tree
      1.8 76.9 42.72×
      MemorySingleMultiScaling
      cache
      552,954 1,269,101 2.30×
      cachehammer
      2,068,413 46,440,180 22.45×
      cacheline
      78.16 6,022 77.05×
      l1cache
      329.41 30,496 92.58×
      memcpy
      688.39 64,353 93.48×
      memrate
      5.93 70.59 11.90×
      memthrash
      328.2 526.18 1.60×
      ptr-chase
      31,751,460 830,212,122 26.15×
      spinmem
      5,569 100,878 18.11×
      stream
      138.25 1,259,844 9112.80×
      vm
      133,407 3,370,944 25.27×

      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
      c8g.medium 12 GiB0
      c8g.large 24 GiB0
      c8g.xlarge 48 GiB0
      c8g.2xlarge 816 GiB0
      c8g.4xlarge 1632 GiB0
      c8g.8xlarge 3264 GiB0
      c8g.12xlarge 4896 GiB0

      Similar Servers #

      INSTANCEVENDORvCPUsMEMORYAccelerators

      c8g.24xlarge FAQs #