m9g.16xlarge by Amazon Web Services

m9g.16xlarge is a General purpose [AWS Graviton processors] Gen9 16xlarge server offered by Amazon Web Services with 64 vCPUs, 256 GiB of memory and 0 GB of storage. The pricing starts at 0.5706 USD per hour.
64 vCPU
256 GiB Memory
Spare SCore
127,950
(All-cores)
2,006
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
m9g.16xlarge
Description
General purpose [AWS Graviton processors] Gen9 16xlarge
Family
m9g
Hw Virt
Average Time To Start
13.67
Status
active
Observed At
2026-10-28T23:25:16.783531

Availability

REGION / IDSPOTONDEMAND
Ohio (US) / us-east-2
1.0527 USD/h 3.1309 USD/h
Northern Virgina (US) / us-east-1
1.052675 USD/h 3.1309 USD/h
Oregon (US) / us-west-2
1.092275 USD/h 3.1309 USD/h
(MY) / ap-southeast-5
1.405467 USD/h 3.3267 USD/h
Aragón (ES) / eu-south-2
0.58005 USD/h 3.4874 USD/h
Dublin (IE) / eu-west-1
1.610967 USD/h 3.4893 USD/h
Frankfurt (DE) / eu-central-1
1.384767 USD/h 3.751 USD/h
Sydney (AU) / ap-southeast-2
0.9387 USD/h 3.9136 USD/h
Singapore (SG) / ap-southeast-1
1.594367 USD/h 3.9136 USD/h
Tokyo (JP) / ap-northeast-1
1.467367 USD/h 4.0442 USD/h

Processor

vCPUs
64
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
64
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
4 MiB
CPU L1I Cache
64 KiB
CPU L1I Cache Total
4 MiB
CPU L2 Cache
2 MiB
CPU L2 Cache Total
128 MiB
CPU L3 Cache
48 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
63.8
Scalability
99.69

System Resources and Accelerators

MEMORY
Memory Amount
256 GiB
Memory Amount Actual
252 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
      34 Gbps
      Network Speed Max
      34 Gbps
      Network Storage Speed Baseline
      24 Gbps
      Network Storage Speed Max
      24 Gbps
      Inbound Traffic
      0 GB/month
      Outbound Traffic
      0 GB/month
      IPv4
      0

      CPU and System Topology

      Server Description

      A dedicated 64-core ARMv9 general-purpose instance delivering top-tier multi-threaded performance and high memory bandwidth for parallel workloads.

      General PurposeCompute Optimized

      Amazon Web Services m9g.16xlarge is a general-purpose server instance utilizing the arm64 architecture and powered by an AWS Graviton ARMv9 Neoverse-V3 processor. It features 64 dedicated physical cores running at 3.3 GHz, 256.0 GB of RAM, and a baseline network bandwidth of 34 Gbps, with no local storage or GPU hardware. Operating on the Nitro hypervisor, the instance delivers top-tier multi-core CPU and memory bandwidth performance, highlighted by strong software compilation and database operation benchmarks. However, single-core performance is average, and LLM text generation speeds are poor. Qualitatively, the instance provides high resource density for parallelized workloads. It is suited for database operations, multi-threaded data processing, software compilation, and static web serving.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      6.8Score
      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) 22,313,536 ops/sec 1,919,289 ops/sec 12 50.00% 50.00% +250.00%
      Redis RPS (pipeline=16, SET) 129,964,645 ops/sec 11,728,058 ops/sec 11 20.00% 20.00% +62.00%
      PassMark Memory Mark (composite) 4,594 2,416 1.9 10.00% 10.00% +6.60%
      Memory bandwidth (read, 16 MB ~ L3) 423,938 MB/sec 108,466 MB/sec 3.8 10.00% 10.00% +14.00%
      PassMark single-thread CPU 2,464 Mops/s 2,365 Mops/s 1 10.00% 10.00% 0.00%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 2,383

      Geekbench Multi-Core

      Score: 30,217

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 60,841
      Compression
      		 595,388
      Encryption
      		 19,046
      Extended Instructions
      		 86,066
      Floating Point Maths
      		 488,778
      Integer Maths
      		 391,059
      Physics
      		 19,066
      Prime Numbers
      		 1,127
      Single Threaded
      		 2,464
      String Sorting
      		 339,653

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 4,594
      Database Operations
      		 58,750
      Memory Latency
      		 26
      Memory Read Cached
      		 22,137
      Memory Read Uncached
      		 24,657
      Memory Write
      		 25,034

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 203.46 12.53 0.06×
      bitops
      		 164,738 10,537,179 63.96×
      branch
      		 319,938 20,422,273 63.83×
      funccall
      		 2,281 144,219 63.24×
      funcret
      		 41,136 2,487,207 60.46×
      hash
      		 181,344 11,553,830 63.71×
      intmath
      		 39,567 2,522,761 63.76×
      nop
      		 429,642 27,218,397 63.35×
      prime
      		 600,465 38,286,007 63.76×
      rotate
      		 149,134 9,504,467 63.73×
      str
      		 932,615 57,310,708 61.45×
      wcs
      		 268,221 17,740,949 66.14×
      CryptographySingleMultiScaling
      crypt
      		 4,286 259,952 60.66×
      CompressionSingleMultiScaling
      jpeg
      		 922.46 58,711 63.65×
      zlib
      		 56.36 3,073 54.52×
      HypervisorSingleMultiScaling
      clock
      		 49,434 341,853 6.92×
      clone
      		 378.46 11,108 29.35×
      context
      		 3,950 258,397 65.42×
      cpu-sched
      		 58.31 4,077 69.92×
      eventfd
      		 143,910 4,459,755 30.99×
      fault
      		 26,906 393,531 14.63×
      fork
      		 6,767 71,259 10.53×
      getrandom
      		 73,960 4,698,669 63.53×
      hrtimers
      		 1,724,302 4,449,374 2.58×
      mprotect
      		 1,160,422 18,980,456 16.36×
      mtx
      		 10,513,829 3,675,760,115 349.61×
      munmap
      		 4,958 118,667 23.93×
      null
      		 682,887 44,087,690 64.56×
      pipe
      		 1,416,726 38,233,184 26.99×
      priv-instr
      		 1,119,838 9,885,249 8.83×
      resched
      		 1,632,015 14,500,052 8.88×
      switch
      		 258,637 40,259,484 155.66×
      timermix
      		 594,913 24,680,474 41.49×
      tlb-shootdown
      		 18,962 247,599 13.06×
      vdso
      		 64,078,776 4,010,775,192 62.59×
      vfork
      		 57,991 385,682 6.65×
      yield
      		 137,075,453 131,660,347 0.96×
      zero
      		 3,263,164 208,431,624 63.87×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 2,244 143,092 63.75×
      expmath
      		 424.87 27,021 63.60×
      fma
      		 852,548 54,058,752 63.41×
      fp
      		 177.6 11,256 63.38×
      fractal
      		 9.2 578.33 62.86×
      hyperbolic
      		 408.05 26,028 63.79×
      logmath
      		 490.96 31,057 63.26×
      matrix
      		 7,965 507,897 63.76×
      matrix-3d
      		 1,458 17,204 11.80×
      monte-carlo
      		 269.62 17,357 64.38×
      mpfr
      		 1,886 120,232 63.74×
      powmath
      		 281.84 17,767 63.04×
      trig
      		 553.32 35,218 63.65×
      veccmp
      		 26,311 1,675,904 63.70×
      vecfp
      		 1,858 118,510 63.78×
      vecmath
      		 4,816 306,222 63.58×
      vecshuf
      		 1,032 65,690 63.67×
      vecwide
      		 30,057 2,061,997 68.60×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 11.2 716.79 64.00×
      bsearch
      		 422 26,756 63.40×
      bubblesort
      		 1.4 89.6 64.00×
      fibsearch
      		 414.26 26,406 63.74×
      heapsort
      		 15.4 975.38 63.34×
      hsearch
      		 10,830 685,913 63.34×
      insertionsort
      		 7.8 492.4 63.13×
      malloc
      		 4,603,510 134,548,643 29.23×
      mcontend
      		 210.91 161,443 765.46×
      mergesort
      		 38.8 2,461 63.43×
      qsort
      		 26.8 1,701 63.46×
      skiplist
      		 7,663 486,528 63.49×
      tree
      		 2.2 80.32 36.51×
      MemorySingleMultiScaling
      cache
      		 620,148 1,991,806 3.21×
      cachehammer
      		 2,302,179 43,176,262 18.75×
      cacheline
      		 72.37 4,877 67.39×
      l1cache
      		 391.51 24,493 62.56×
      memcpy
      		 1,016 61,166 60.18×
      memrate
      		 6.93 60.7 8.76×
      memthrash
      		 302.87 461.34 1.52×
      ptr-chase
      		 37,606,047 721,741,390 19.19×
      spinmem
      		 6,557 69,557 10.61×
      stream
      		 59.2 53,226 899.09×
      vm
      		 203,973 6,344,705 31.11×

      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.16xlarge FAQs