m8g.24xlarge by Amazon Web Services

m8g.24xlarge is a General purpose [AWS Graviton processors] Gen8 24xlarge server offered by Amazon Web Services with 96 vCPUs, 384 GiB of memory and 0 GB of storage. The pricing starts at 0.308 USD per hour.
96 vCPU
384 GiB Memory
Spare SCore
163,469
(All-cores)
1,706
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
m8g.24xlarge
Description
General purpose [AWS Graviton processors] Gen8 24xlarge
Family
m8g
Hw Virt
Average Time To Start
8.5
Status
active
Observed At
2026-10-22T09:55:09.813875

Availability

REGION / IDSPOTONDEMAND
Hyderabad (IN) / ap-south-2
0.3453 USD/h 3.0797 USD/h
Mumbai (IN) / ap-south-1
1.1678 USD/h 3.0797 USD/h
Northern Virgina (US) / us-east-1
1.3202 USD/h 4.3085 USD/h
Ohio (US) / us-east-2
1.277067 USD/h 4.3085 USD/h
Oregon (US) / us-west-2
1.629375 USD/h 4.3085 USD/h
(MX) / mx-central-1
1.609667 USD/h 4.5235 USD/h
Stockholm (SE) / eu-north-1
0.582667 USD/h 4.5782 USD/h
(TH) / ap-southeast-7
1.639867 USD/h 4.5782 USD/h
(MY) / ap-southeast-5
1.516767 USD/h 4.5782 USD/h
Aragón (ES) / eu-south-2
0.535167 USD/h 4.799 USD/h
Dublin (IE) / eu-west-1
2.303367 USD/h 4.8019 USD/h
Quebec (CA) / ca-central-1
0.883433 USD/h 4.8029 USD/h
Calgary (CA) / ca-west-1
1.5818 USD/h 4.8029 USD/h
London (GB) / eu-west-2
1.1911 USD/h 4.9824 USD/h
Taipei (TW) / ap-east-2
1.674367 USD/h 5.0083 USD/h
Milan (IT) / eu-south-1
0.8835 USD/h 5.0266 USD/h
California (US) / us-west-1
1.28665 USD/h 5.0266 USD/h
Paris (FR) / eu-west-3
1.5146 USD/h 5.0266 USD/h
Frankfurt (DE) / eu-central-1
1.500667 USD/h 5.1619 USD/h
United Arab Emirates / me-central-1
2.1623 USD/h 5.2819 USD/h
Seoul (KR) / ap-northeast-2
1.0881 USD/h 5.2963 USD/h
Jakarta (ID) / ap-southeast-3
0.5386 USD/h 5.3856 USD/h
Sydney (AU) / ap-southeast-2
1.5984 USD/h 5.3856 USD/h
Melbourne (AU) / ap-southeast-4
1.627533 USD/h 5.3856 USD/h
Singapore (SG) / ap-southeast-1
1.992833 USD/h 5.3856 USD/h
Tokyo (JP) / ap-northeast-1
1.9461 USD/h 5.5651 USD/h
Osaka (JP) / ap-northeast-3
1.968133 USD/h 5.5651 USD/h
Zurich (CH) / eu-central-2
1.623933 USD/h 5.6774 USD/h
Cape Town (ZA) / af-south-1
1.251667 USD/h 5.7005 USD/h
Hong Kong (HK) / ap-east-1
0.6945 USD/h 5.9242 USD/h
Sao Paulo (BR) / sa-east-1
2.7025 USD/h 6.8669 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
384 GiB
Memory Amount Actual
378 GiB
ACCELERATORS
Accelerator Count
0
Accelerator Memory Min
0 MiB
Accelerator Memory Total
0 MiB
Accelerators
    STORAGE
    Storage Size
    0 GB
    Storages
      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

      A dedicated 96-core ARM64 server delivering top-tier multi-threaded throughput and high memory bandwidth for parallelized enterprise workloads.

      General Purpose

      The Amazon Web Services m8g.24xlarge is an ARM64 general-purpose server instance powered by 96 dedicated AWS Graviton Neoverse-V2 physical cores running at 2.8 GHz. Operating on the Nitro hypervisor, it features 384.0 GB of system memory, 40 Gbps baseline network bandwidth, and no local storage or GPU. Benchmarks reveal top-tier multi-core CPU performance, high memory bandwidth, and exceptional throughput in database operations, static web serving, and Redis SET operations. However, single-core performance remains average, presenting a tradeoff where parallel execution is highly prioritized over single-threaded speed. This hardware profile delivers qualitative cost efficiency for highly concurrent workloads, making it suitable for large-scale web serving, software compilation, database management, and multi-threaded enterprise applications.

      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) 22,582,226 ops/sec 1,918,343 ops/sec 12 50.00% 50.00% +250.00%
      Redis RPS (pipeline=16, SET) 120,749,656 ops/sec 11,704,734 ops/sec 10 20.00% 20.00% +58.00%
      PassMark Memory Mark (composite) 3,376 2,416 1.4 10.00% 10.00% +3.40%
      Memory bandwidth (read, 16 MB ~ L3) 548,112 MB/sec 108,420 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: 1,882

      Geekbench Multi-Core

      Score: 26,119

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 56,760
      Compression
      		 637,487
      Encryption
      		 18,067
      Extended Instructions
      		 80,664
      Floating Point Maths
      		 581,212
      Integer Maths
      		 500,272
      Physics
      		 19,397
      Prime Numbers
      		 845
      Single Threaded
      		 1,944
      String Sorting
      		 434,627

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 3,376
      Database Operations
      		 47,322
      Memory Latency
      		 48
      Memory Read Cached
      		 21,177
      Memory Read Uncached
      		 20,223
      Memory Write
      		 21,290

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 138.08 - -
      bitops
      		 144,841 13,866,824 95.74×
      branch
      		 227,038 21,760,186 95.84×
      funccall
      		 1,971 188,879 95.81×
      funcret
      		 34,579 2,657,162 76.84×
      hash
      		 155,637 14,905,724 95.77×
      intmath
      		 32,626 3,138,205 96.19×
      nop
      		 454,891 43,647,164 95.95×
      prime
      		 499,740 47,876,024 95.80×
      rotate
      		 134,280 12,839,621 95.62×
      str
      		 751,953 66,459,073 88.38×
      wcs
      		 201,802 19,396,127 96.11×
      CryptographySingleMultiScaling
      crypt
      		 3,522 331,827 94.22×
      CompressionSingleMultiScaling
      jpeg
      		 739.99 55,096 74.46×
      zlib
      		 48.65 3,877 79.70×
      HypervisorSingleMultiScaling
      clock
      		 42,708 253,144 5.93×
      clone
      		 373.95 14,697 39.30×
      context
      		 3,419 330,923 96.78×
      cpu-sched
      		 59.5 6,072 102.05×
      eventfd
      		 94,599 3,190,308 33.72×
      fault
      		 24,586 374,066 15.21×
      fork
      		 5,375 76,300 14.20×
      getrandom
      		 62,231 5,966,911 95.88×
      hrtimers
      		 618,968 14,069,412 22.73×
      mprotect
      		 1,341,188 21,728,411 16.20×
      mtx
      		 8,866,545 4,514,530,708 509.16×
      munmap
      		 3,957 109,858 27.76×
      null
      		 592,792 57,288,868 96.64×
      pipe
      		 1,141,509 49,130,645 43.04×
      priv-instr
      		 903,154 12,041,589 13.33×
      resched
      		 2,590,869 8,855,861 3.42×
      switch
      		 179,765 52,449,699 291.77×
      timermix
      		 569,214 54,627,701 95.97×
      tlb-shootdown
      		 16,221 283,261 17.46×
      vdso
      		 44,391,769 4,246,182,556 95.65×
      vfork
      		 36,272 256,444 7.07×
      yield
      		 128,072,916 137,179,020 1.07×
      zero
      		 2,797,502 268,900,280 96.12×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 1,935 185,389 95.80×
      expmath
      		 366.62 35,139 95.85×
      fma
      		 775,487 65,549,706 84.53×
      fp
      		 151.2 14,670 97.03×
      fractal
      		 7.8 734.56 94.17×
      hyperbolic
      		 354.13 33,902 95.73×
      logmath
      		 429.44 41,151 95.83×
      matrix
      		 6,603 632,195 95.74×
      matrix-3d
      		 1,363 22,582 16.56×
      monte-carlo
      		 237.15 22,865 96.42×
      mpfr
      		 1,437 137,206 95.50×
      powmath
      		 248.99 23,862 95.84×
      trig
      		 475.9 45,629 95.88×
      veccmp
      		 21,810 2,091,262 95.89×
      vecfp
      		 1,241 111,095 89.55×
      vecmath
      		 4,445 426,090 95.86×
      vecshuf
      		 882.02 84,519 95.82×
      vecwide
      		 25,214 2,201,705 87.32×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 9 863.58 95.95×
      bsearch
      		 341.3 32,711 95.84×
      bubblesort
      		 1.2 115.2 96.00×
      fibsearch
      		 365.11 34,971 95.78×
      heapsort
      		 13 1,247 95.92×
      hsearch
      		 8,492 812,254 95.65×
      insertionsort
      		 6.8 641 94.26×
      malloc
      		 3,812,660 207,936,520 54.54×
      mcontend
      		 264.26 195,497 739.79×
      mergesort
      		 33.4 3,178 95.15×
      qsort
      		 22.4 2,135 95.29×
      skiplist
      		 6,745 645,319 95.67×
      tree
      		 2 76.51 38.26×
      MemorySingleMultiScaling
      cache
      		 559,573 1,273,242 2.28×
      cachehammer
      		 2,070,072 46,229,429 22.33×
      cacheline
      		 81.77 6,096 74.55×
      l1cache
      		 329.61 30,563 92.73×
      memcpy
      		 688.06 64,321 93.48×
      memrate
      		 5.93 70.42 11.88×
      memthrash
      		 339 528.95 1.56×
      ptr-chase
      		 32,298,830 832,081,205 25.76×
      spinmem
      		 4,513 100,623 22.30×
      stream
      		 134.17 1,258,097 9376.88×
      vm
      		 133,280 3,209,981 24.08×

      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
      m8g.medium 14 GiB0
      m8g.large 28 GiB0
      m8g.xlarge 416 GiB0
      m8g.2xlarge 832 GiB0
      m8g.4xlarge 1664 GiB0
      m8g.8xlarge 32128 GiB0
      m8g.12xlarge 48192 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      m8g.24xlarge FAQs