m8g.metal-24xl by Amazon Web Services

m8g.metal-24xl is a General purpose [AWS Graviton processors] Gen8 metal-24xl 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
163,914
(All-cores)
1,710
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
m8g.metal-24xl
Description
General purpose [AWS Graviton processors] Gen8 metal-24xl
Family
m8g
Hw Virt
Average Time To Start
12
Status
active
Observed At
2026-10-29T02:46:22.891489

Availability

REGION / IDSPOTONDEMAND
Hyderabad (IN) / ap-south-2
0.308 USD/h 3.0797 USD/h
Mumbai (IN) / ap-south-1
0.9031 USD/h 3.0797 USD/h
Ohio (US) / us-east-2
0.861633 USD/h 4.3085 USD/h
Northern Virgina (US) / us-east-1
1.24548 USD/h 4.3085 USD/h
Oregon (US) / us-west-2
1.6702 USD/h 4.3085 USD/h
(MX) / mx-central-1
3.547733 USD/h 4.5235 USD/h
(TH) / ap-southeast-7
1.154333 USD/h 4.5782 USD/h
Stockholm (SE) / eu-north-1
0.4578 USD/h 4.5782 USD/h
(MY) / ap-southeast-5
2.218867 USD/h 4.5782 USD/h
Aragón (ES) / eu-south-2
0.5409 USD/h 4.799 USD/h
Dublin (IE) / eu-west-1
1.808833 USD/h 4.8019 USD/h
Quebec (CA) / ca-central-1
0.751067 USD/h 4.8029 USD/h
Calgary (CA) / ca-west-1
1.91865 USD/h 4.8029 USD/h
London (GB) / eu-west-2
0.634925 USD/h 4.9824 USD/h
Taipei (TW) / ap-east-2
2.537933 USD/h 5.0083 USD/h
California (US) / us-west-1
0.6796 USD/h 5.0266 USD/h
Paris (FR) / eu-west-3
0.880233 USD/h 5.0266 USD/h
Milan (IT) / eu-south-1
1.1033 USD/h 5.0266 USD/h
Frankfurt (DE) / eu-central-1
0.961 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
0.754775 USD/h 5.2963 USD/h
Jakarta (ID) / ap-southeast-3
0.5386 USD/h 5.3856 USD/h
Melbourne (AU) / ap-southeast-4
1.041767 USD/h 5.3856 USD/h
Sydney (AU) / ap-southeast-2
0.8633 USD/h 5.3856 USD/h
Singapore (SG) / ap-southeast-1
2.0731 USD/h 5.3856 USD/h
Tokyo (JP) / ap-northeast-1
1.686433 USD/h 5.5651 USD/h
Osaka (JP) / ap-northeast-3
1.535567 USD/h 5.5651 USD/h
Zurich (CH) / eu-central-2
1.842 USD/h 5.6774 USD/h
Cape Town (ZA) / af-south-1
0.9777 USD/h 5.7005 USD/h
Hong Kong (HK) / ap-east-1
0.837 USD/h 5.9242 USD/h
Sao Paulo (BR) / sa-east-1
0.6867 USD/h 6.8669 USD/h

Processor

vCPUs
96
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
95.9
Scalability
99.9

System Resources and Accelerators

MEMORY
Memory Amount
384 GiB
Memory Amount Actual
384 GiB
Memory Generation
DDR5
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 high-density, bare-metal ARMv9 server delivering exceptional multi-core performance and memory bandwidth for enterprise database and web-serving workloads.

      General Purpose

      The Amazon Web Services m8g.metal-24xl is a bare-metal general-purpose server featuring 96 dedicated physical cores on the ARMv9 AWS Graviton Neoverse-V2 architecture running at 2.8 GHz. Equipped with 384.0 GB of DDR5 memory, it provides a balanced 4.0 GB of RAM per core, though it lacks local storage and GPU accelerators. The server delivers top-tier multi-core performance, memory bandwidth, and database operations, as evidenced by outstanding results in multi-threaded benchmarks, Redis SET operations, and software compilation. Conversely, single-core performance remains average, and text generation for small language models is a notable bottleneck. With a baseline network bandwidth of 40 Gbps, this instance is highly suited for parallelized workloads, including database hosting, high-throughput web serving, and software compilation, offering strong resource density and qualitative cost-efficiency for multi-threaded enterprise applications.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      6.2Score
      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) 21,081,297 ops/sec 1,919,289 ops/sec 11 50.00% 50.00% +230.00%
      Redis RPS (pipeline=16, SET) 121,894,518 ops/sec 11,728,058 ops/sec 10 20.00% 20.00% +58.00%
      PassMark Memory Mark (composite) 3,399 2,416 1.4 10.00% 10.00% +3.40%
      Memory bandwidth (read, 16 MB ~ L3) 543,951 MB/sec 108,466 MB/sec 4.9 10.00% 10.00% +17.00%
      PassMark single-thread CPU 1,949 Mops/s 2,365 Mops/s 0.79 10.00% 10.00% -2.30%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,898

      Geekbench Multi-Core

      Score: 26,773

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 56,912
      Compression
      		 639,030
      Encryption
      		 18,120
      Extended Instructions
      		 80,527
      Floating Point Maths
      		 582,575
      Integer Maths
      		 501,305
      Physics
      		 19,689
      Prime Numbers
      		 865
      Single Threaded
      		 1,949
      String Sorting
      		 435,549

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 3,399
      Database Operations
      		 47,629
      Memory Latency
      		 47
      Memory Read Cached
      		 21,177
      Memory Read Uncached
      		 20,152
      Memory Write
      		 21,251

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 156.76 - -
      bitops
      		 145,004 13,875,948 95.69×
      branch
      		 227,521 21,787,065 95.76×
      funccall
      		 1,975 189,175 95.78×
      funcret
      		 34,318 2,675,359 77.96×
      hash
      		 155,915 14,913,011 95.65×
      intmath
      		 32,929 3,143,654 95.47×
      nop
      		 456,241 43,621,728 95.61×
      prime
      		 500,277 47,954,148 95.86×
      rotate
      		 134,506 12,834,442 95.42×
      str
      		 753,225 68,312,947 90.69×
      wcs
      		 201,361 19,454,596 96.62×
      CryptographySingleMultiScaling
      crypt
      		 3,467 332,666 95.94×
      CompressionSingleMultiScaling
      jpeg
      		 744.72 54,947 73.78×
      zlib
      		 50.28 3,798 75.54×
      HypervisorSingleMultiScaling
      clock
      		 46,656 254,123 5.45×
      clone
      		 365.95 14,146 38.66×
      context
      		 3,648 330,125 90.50×
      cpu-sched
      		 64.32 6,082 94.56×
      eventfd
      		 140,178 4,405,255 31.43×
      fault
      		 25,121 391,405 15.58×
      fork
      		 5,890 79,719 13.53×
      getrandom
      		 62,369 5,970,307 95.73×
      hrtimers
      		 126,050 9,654,610 76.59×
      mprotect
      		 1,466,995 22,957,551 15.65×
      mtx
      		 10,069,743 4,295,551,240 426.58×
      munmap
      		 4,162 139,880 33.61×
      null
      		 594,628 57,212,709 96.22×
      pipe
      		 1,197,689 50,093,109 41.82×
      priv-instr
      		 918,488 12,909,547 14.06×
      resched
      		 2,347,164 8,691,527 3.70×
      switch
      		 251,349 52,766,202 209.93×
      timermix
      		 787,455 75,310,327 95.64×
      tlb-shootdown
      		 18,439 301,881 16.37×
      vdso
      		 45,133,117 4,255,445,833 94.29×
      vfork
      		 45,204 375,713 8.31×
      yield
      		 129,684,740 138,841,905 1.07×
      zero
      		 2,804,023 269,583,770 96.14×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 1,940 185,751 95.77×
      expmath
      		 367.41 35,185 95.77×
      fma
      		 777,182 65,552,777 84.35×
      fp
      		 155.11 14,703 94.79×
      fractal
      		 7.8 734.73 94.20×
      hyperbolic
      		 354.76 33,950 95.70×
      logmath
      		 429.36 41,224 96.01×
      matrix
      		 6,620 632,394 95.52×
      matrix-3d
      		 1,393 23,486 16.86×
      monte-carlo
      		 236.93 22,844 96.42×
      mpfr
      		 1,440 138,125 95.91×
      powmath
      		 249.42 23,904 95.84×
      trig
      		 476.79 45,667 95.78×
      veccmp
      		 21,851 2,090,979 95.69×
      vecfp
      		 1,243 111,201 89.48×
      vecmath
      		 4,453 426,345 95.75×
      vecshuf
      		 885.29 84,372 95.30×
      vecwide
      		 25,126 2,199,448 87.54×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 9 863.78 95.98×
      bsearch
      		 342.24 32,774 95.76×
      bubblesort
      		 1.2 115.2 96.00×
      fibsearch
      		 365.56 34,980 95.69×
      heapsort
      		 13 1,247 95.92×
      hsearch
      		 8,612 806,960 93.70×
      insertionsort
      		 6.8 647.2 95.18×
      malloc
      		 4,180,304 207,506,108 49.64×
      mcontend
      		 253.24 198,757 784.86×
      mergesort
      		 33.4 3,205 95.95×
      qsort
      		 22.4 2,137 95.39×
      skiplist
      		 6,753 647,531 95.88×
      tree
      		 1.8 86.45 48.03×
      MemorySingleMultiScaling
      cache
      		 558,842 1,269,303 2.27×
      cachehammer
      		 2,083,160 49,644,279 23.83×
      cacheline
      		 78.17 6,022 77.03×
      l1cache
      		 331.21 30,559 92.27×
      memcpy
      		 689.28 64,293 93.28×
      memrate
      		 5.93 71.02 11.98×
      memthrash
      		 376.57 525.04 1.39×
      ptr-chase
      		 34,479,687 854,736,367 24.79×
      spinmem
      		 4,449 111,186 24.99×
      stream
      		 134.49 1,263,254 9392.92×
      vm
      		 140,269 3,228,616 23.02×

      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.metal-24xl FAQs