m9g.24xlarge by Amazon Web Services

m9g.24xlarge is a General purpose [AWS Graviton processors] Gen9 24xlarge server offered by Amazon Web Services with 96 vCPUs, 384 GiB of memory and 0 GB of storage. The pricing starts at 0.8608 USD per hour.
96 vCPU
384 GiB Memory
Spare SCore
191,594
(All-cores)
1,999
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
m9g.24xlarge
Description
General purpose [AWS Graviton processors] Gen9 24xlarge
Family
m9g
Hw Virt
Average Time To Start
12.33
Status
active
Observed At
2026-10-28T23:25:16.782816

Availability

REGION / IDSPOTONDEMAND
Ohio (US) / us-east-2
1.525567 USD/h 4.6963 USD/h
Northern Virgina (US) / us-east-1
1.7101 USD/h 4.6963 USD/h
Oregon (US) / us-west-2
1.7617 USD/h 4.6963 USD/h
(MY) / ap-southeast-5
1.4799 USD/h 4.9901 USD/h
Aragón (ES) / eu-south-2
0.88625 USD/h 5.231 USD/h
Dublin (IE) / eu-west-1
2.448 USD/h 5.2339 USD/h
Frankfurt (DE) / eu-central-1
1.815533 USD/h 5.6266 USD/h
Sydney (AU) / ap-southeast-2
1.2605 USD/h 5.8704 USD/h
Singapore (SG) / ap-southeast-1
2.0089 USD/h 5.8704 USD/h
Tokyo (JP) / ap-northeast-1
2.038367 USD/h 6.0662 USD/h

Processor

vCPUs
96
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
96
CPU Speed
3.3 GHz
CPU Architecture
arm64
CPU Manufacturer
AWS
CPU Family
ARMv9
CPU Model
Neoverse-V3
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
96 MiB
CPU L3 Cache Total
96 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, sb, paca, pacg, dcpodp, sve2, sveaes, svepmull, svebitperm, svesha3, flagm2, frint, svei8mm, svebf16, i8mm, bf16, dgh, rng, bti, ecv, afp, wfxt
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
      50 Gbps
      Network Speed Max
      50 Gbps
      Network Storage Speed Baseline
      36 Gbps
      Network Storage Speed Max
      36 Gbps
      Inbound Traffic
      0 GB/month
      Outbound Traffic
      0 GB/month
      IPv4
      0

      CPU and System Topology

      Server Description

      A high-density ARM64 server delivering exceptional multi-core compute, top-tier memory bandwidth, and balanced resources for demanding enterprise workloads.

      General PurposeCompute Optimized

      Amazon Web Services m9g.24xlarge is a general-purpose server powered by 96 dedicated ARM64 physical cores using the AWS Graviton Neoverse-V3 processor at 3.3 GHz. Operating on the Nitro hypervisor, it features 384.0 GB of RAM, a 50 Gbps baseline network bandwidth, and no local storage or GPUs. The server delivers top-tier multi-core performance, highlighted by a stress-ng multi-core score of 191594.32 and exceptional memory bandwidth, reaching 13865.98 GB/sec for small block reads. It excels in data processing, showing top-tier results in bzip3 decompression and Redis SET operations at 266.43 million operations per second. This instance is highly efficient for multi-threaded applications, database operations, static web serving, and lightweight language model prompt processing, offering a balanced resource profile for enterprise workloads.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      8.7Score
      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) 32,409,876 ops/sec 1,919,289 ops/sec 17 50.00% 50.00% +310.00%
      Redis RPS (pipeline=16, SET) 191,386,909 ops/sec 11,728,058 ops/sec 16 20.00% 20.00% +74.00%
      PassMark Memory Mark (composite) 4,603 2,416 1.9 10.00% 10.00% +6.60%
      Memory bandwidth (read, 16 MB ~ L3) 419,559 MB/sec 108,466 MB/sec 3.8 10.00% 10.00% +14.00%
      PassMark single-thread CPU 2,462 Mops/s 2,365 Mops/s 1 10.00% 10.00% 0.00%

      Memory Bandwidth

      Compression

      OpenSSL

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 77,011
      Compression
      		 885,574
      Encryption
      		 28,396
      Extended Instructions
      		 128,809
      Floating Point Maths
      		 731,565
      Integer Maths
      		 585,512
      Physics
      		 21,018
      Prime Numbers
      		 1,108
      Single Threaded
      		 2,462
      String Sorting
      		 493,015

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 4,603
      Database Operations
      		 57,589
      Memory Latency
      		 29
      Memory Read Cached
      		 24,775
      Memory Read Uncached
      		 24,537
      Memory Write
      		 24,932

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 173.96 9.76 0.06×
      bitops
      		 165,693 15,786,268 95.27×
      branch
      		 319,996 30,562,905 95.51×
      funccall
      		 2,280 217,789 95.52×
      funcret
      		 40,001 3,835,478 95.88×
      hash
      		 181,309 17,305,140 95.45×
      intmath
      		 39,664 3,780,642 95.32×
      nop
      		 429,368 41,038,417 95.58×
      prime
      		 600,048 57,375,659 95.62×
      rotate
      		 149,042 14,222,703 95.43×
      str
      		 937,270 89,481,903 95.47×
      wcs
      		 279,334 26,750,428 95.77×
      CryptographySingleMultiScaling
      crypt
      		 4,359 407,929 93.58×
      CompressionSingleMultiScaling
      jpeg
      		 893.43 68,790 77.00×
      zlib
      		 42.52 4,455 104.78×
      HypervisorSingleMultiScaling
      clock
      		 46,407 269,888 5.82×
      clone
      		 325.89 11,734 36.01×
      context
      		 3,949 380,840 96.44×
      cpu-sched
      		 71.22 5,861 82.29×
      eventfd
      		 148,322 4,571,124 30.82×
      fault
      		 26,739 367,285 13.74×
      fork
      		 5,938 66,975 11.28×
      getrandom
      		 73,996 7,068,745 95.53×
      hrtimers
      		 270,502 6,661,003 24.62×
      mprotect
      		 1,151,034 19,314,946 16.78×
      mtx
      		 12,184,912 5,662,666,272 464.73×
      munmap
      		 4,568 113,881 24.93×
      null
      		 680,695 65,636,469 96.43×
      pipe
      		 1,011,397 49,701,412 49.14×
      priv-instr
      		 1,100,326 10,817,718 9.83×
      resched
      		 1,706,202 17,628,264 10.33×
      switch
      		 225,655 65,435,392 289.98×
      timermix
      		 594,646 22,898,043 38.51×
      tlb-shootdown
      		 16,170 250,465 15.49×
      vdso
      		 64,124,952 5,905,989,133 92.10×
      vfork
      		 47,946 364,381 7.60×
      yield
      		 156,202,762 183,040,296 1.17×
      zero
      		 3,320,115 312,120,302 94.01×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 2,243 214,156 95.48×
      expmath
      		 424.51 40,583 95.60×
      fma
      		 852,821 81,460,182 95.52×
      fp
      		 175.2 16,822 96.02×
      fractal
      		 9.2 866.16 94.15×
      hyperbolic
      		 407.98 38,925 95.41×
      logmath
      		 491.09 46,903 95.51×
      matrix
      		 7,975 761,090 95.43×
      matrix-3d
      		 1,515 17,011 11.23×
      monte-carlo
      		 269.48 25,959 96.33×
      mpfr
      		 1,888 180,173 95.44×
      powmath
      		 281.8 26,905 95.48×
      trig
      		 553.28 52,809 95.45×
      veccmp
      		 26,327 2,515,004 95.53×
      vecfp
      		 1,851 176,433 95.32×
      vecmath
      		 4,811 460,593 95.74×
      vecshuf
      		 1,031 98,097 95.11×
      vecwide
      		 30,053 2,870,146 95.50×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 11.2 1,067 95.25×
      bsearch
      		 422.04 40,311 95.51×
      bubblesort
      		 1.4 134.4 96.00×
      fibsearch
      		 413.96 39,535 95.51×
      heapsort
      		 15.4 1,458 94.70×
      hsearch
      		 10,829 1,023,034 94.47×
      insertionsort
      		 8 739 92.38×
      malloc
      		 4,298,253 190,295,002 44.27×
      mcontend
      		 217.3 239,749 1103.31×
      mergesort
      		 38.6 3,645 94.44×
      qsort
      		 26.8 2,537 94.65×
      skiplist
      		 7,649 731,302 95.61×
      tree
      		 1.8 95.63 53.13×
      MemorySingleMultiScaling
      cache
      		 690,742 2,447,095 3.54×
      cachehammer
      		 2,303,235 33,431,747 14.52×
      cacheline
      		 72.77 5,575 76.61×
      l1cache
      		 390.68 35,905 91.90×
      memcpy
      		 1,017 91,438 89.92×
      memrate
      		 6.33 51.99 8.21×
      memthrash
      		 283.54 536.53 1.89×
      ptr-chase
      		 27,542,141 857,522,051 31.13×
      spinmem
      		 5,858 81,747 13.96×
      stream
      		 52.87 123,828 2342.12×
      vm
      		 196,227 3,126,719 15.93×

      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
      m9g.medium 14 GiB0
      m9g.large 28 GiB0
      m9g.xlarge 416 GiB0
      m9g.2xlarge 832 GiB0
      m9g.4xlarge 1664 GiB0
      m9g.8xlarge 32128 GiB0
      m9g.12xlarge 48192 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      m9g.24xlarge FAQs