m9g.4xlarge by Amazon Web Services

m9g.4xlarge is a General purpose [AWS Graviton processors] Gen9 4xlarge server offered by Amazon Web Services with 16 vCPUs, 64 GiB of memory and 0 GB of storage. The pricing starts at 0.1391 USD per hour.
16 vCPU
64 GiB Memory
Spare SCore
32,101
(All-cores)
2,009
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
m9g.4xlarge
Description
General purpose [AWS Graviton processors] Gen9 4xlarge
Family
m9g
Hw Virt
Average Time To Start
12.33
Status
active
Observed At
2026-10-28T19:56:30.296662

Availability

REGION / IDSPOTONDEMAND
Ohio (US) / us-east-2
0.2479 USD/h 0.7827 USD/h
Oregon (US) / us-west-2
0.29425 USD/h 0.7827 USD/h
Northern Virgina (US) / us-east-1
0.32365 USD/h 0.7827 USD/h
(MY) / ap-southeast-5
0.244933 USD/h 0.8317 USD/h
Aragón (ES) / eu-south-2
0.14075 USD/h 0.8718 USD/h
Dublin (IE) / eu-west-1
0.4136 USD/h 0.8723 USD/h
Frankfurt (DE) / eu-central-1
0.380267 USD/h 0.9378 USD/h
Sydney (AU) / ap-southeast-2
0.377567 USD/h 0.9784 USD/h
Singapore (SG) / ap-southeast-1
0.434133 USD/h 0.9784 USD/h
Tokyo (JP) / ap-northeast-1
0.418767 USD/h 1.011 USD/h

Processor

vCPUs
16
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
16
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
1 MiB
CPU L1I Cache
64 KiB
CPU L1I Cache Total
1 MiB
CPU L2 Cache
2 MiB
CPU L2 Cache Total
32 MiB
CPU L3 Cache
48 MiB
CPU L3 Cache Total
48 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
16
Scalability
100

System Resources and Accelerators

MEMORY
Memory Amount
64 GiB
Memory Amount Actual
63 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
      8.5 Gbps
      Network Speed Max
      17 Gbps
      Network Storage Speed Baseline
      6 Gbps
      Network Storage Speed Max
      12 Gbps
      Inbound Traffic
      0 GB/month
      Outbound Traffic
      0 GB/month
      IPv4
      0

      CPU and System Topology

      Server Description

      An efficient ARM64 general-purpose platform delivering high single-core performance and exceptional memory bandwidth for balanced workloads.

      General Purpose

      The Amazon Web Services m9g.4xlarge is a general-purpose ARM64 server powered by 16 dedicated AWS Graviton Neoverse-V3 physical cores running at 3.3 GHz. Operating on the Nitro hypervisor, it features 64.0 GB of system memory, providing a balanced 4.0 GB of RAM per core, alongside a baseline network bandwidth of 8 Gbps. It does not include local storage or integrated GPUs. Benchmarks reveal top-tier single-core efficiency, highlighted by strong single-threaded compression and high memory performance scores. Multi-core performance is robust, with notable results in database operations and static web serving. Lacking x86-specific instruction sets and local NVMe drives, this instance is optimized for workloads that benefit from high memory bandwidth and efficient ARM architecture, such as database hosting, web serving, text processing, and small-to-medium scale language model inference.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      2.5Score
      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) 5,763,782 ops/sec 1,919,289 ops/sec 3.1 50.00% 50.00% +76.00%
      Redis RPS (pipeline=16, SET) 33,268,682 ops/sec 11,728,058 ops/sec 2.8 20.00% 20.00% +23.00%
      PassMark Memory Mark (composite) 4,553 2,416 1.9 10.00% 10.00% +6.60%
      Memory bandwidth (read, 16 MB ~ L3) 238,718 MB/sec 108,466 MB/sec 2.2 10.00% 10.00% +8.20%
      PassMark single-thread CPU 2,465 Mops/s 2,365 Mops/s 1 10.00% 10.00% 0.00%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 2,334

      Geekbench Multi-Core

      Score: 19,581

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 20,551
      Compression
      		 149,560
      Encryption
      		 4,748
      Extended Instructions
      		 21,584
      Floating Point Maths
      		 122,519
      Integer Maths
      		 98,015
      Physics
      		 6,145
      Prime Numbers
      		 331
      Single Threaded
      		 2,465
      String Sorting
      		 86,293

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 4,553
      Database Operations
      		 29,240
      Memory Latency
      		 26
      Memory Read Cached
      		 24,216
      Memory Read Uncached
      		 24,716
      Memory Write
      		 25,047

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 183.62 72.87 0.40×
      bitops
      		 165,242 2,642,838 15.99×
      branch
      		 320,207 5,117,947 15.98×
      funccall
      		 2,282 36,443 15.97×
      funcret
      		 41,022 632,677 15.42×
      hash
      		 181,377 2,897,897 15.98×
      intmath
      		 39,666 632,743 15.95×
      nop
      		 429,450 6,860,201 15.97×
      prime
      		 599,320 9,601,396 16.02×
      rotate
      		 149,119 2,380,125 15.96×
      str
      		 934,610 14,927,165 15.97×
      wcs
      		 279,116 4,467,314 16.01×
      CryptographySingleMultiScaling
      crypt
      		 4,304 68,625 15.94×
      CompressionSingleMultiScaling
      jpeg
      		 926.04 14,764 15.94×
      zlib
      		 42.8 753.64 17.61×
      HypervisorSingleMultiScaling
      clock
      		 55,197 545,945 9.89×
      clone
      		 407.1 4,284 10.52×
      context
      		 3,954 67,219 17.00×
      cpu-sched
      		 66.44 1,040 15.66×
      eventfd
      		 154,247 3,573,163 23.17×
      fault
      		 29,939 321,930 10.75×
      fork
      		 7,803 67,327 8.63×
      getrandom
      		 74,037 1,183,954 15.99×
      hrtimers
      		 1,143,448 2,609,066 2.28×
      mprotect
      		 1,402,491 9,045,004 6.45×
      mtx
      		 9,788,804 752,752,136 76.90×
      munmap
      		 5,445 67,369 12.37×
      null
      		 680,806 11,285,253 16.58×
      pipe
      		 1,327,899 15,296,733 11.52×
      priv-instr
      		 1,113,352 13,902,015 12.49×
      resched
      		 6,916,209 4,499,451 0.65×
      switch
      		 267,427 11,065,272 41.38×
      timermix
      		 591,361 8,751,720 14.80×
      tlb-shootdown
      		 27,166 130,558 4.81×
      vdso
      		 64,164,732 990,698,798 15.44×
      vfork
      		 69,206 426,765 6.17×
      yield
      		 26,955,222 27,689,469 1.03×
      zero
      		 3,260,886 52,922,872 16.23×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 2,245 35,844 15.97×
      expmath
      		 425.24 6,792 15.97×
      fma
      		 852,897 13,619,450 15.97×
      fp
      		 177.6 2,816 15.85×
      fractal
      		 9.2 145.2 15.78×
      hyperbolic
      		 408.45 6,524 15.97×
      logmath
      		 491.37 7,847 15.97×
      matrix
      		 7,970 127,293 15.97×
      matrix-3d
      		 1,461 9,578 6.55×
      monte-carlo
      		 269.53 4,415 16.38×
      mpfr
      		 1,889 30,176 15.97×
      powmath
      		 281.9 4,501 15.97×
      trig
      		 553.15 8,842 15.99×
      veccmp
      		 26,341 420,836 15.98×
      vecfp
      		 1,860 29,695 15.96×
      vecmath
      		 4,814 76,921 15.98×
      vecshuf
      		 1,032 16,458 15.95×
      vecwide
      		 32,398 516,393 15.94×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 11.2 179.2 16.00×
      bsearch
      		 422.33 6,754 15.99×
      bubblesort
      		 1.4 22.4 16.00×
      fibsearch
      		 413.83 6,618 15.99×
      heapsort
      		 15.4 246 15.97×
      hsearch
      		 10,815 172,785 15.98×
      insertionsort
      		 8 122.6 15.32×
      malloc
      		 4,449,386 51,847,219 11.65×
      mcontend
      		 294.94 37,836 128.28×
      mergesort
      		 38.8 619.38 15.96×
      qsort
      		 26.8 428.19 15.98×
      skiplist
      		 7,671 122,500 15.97×
      tree
      		 2.2 25.58 11.63×
      MemorySingleMultiScaling
      cache
      		 720,896 1,571,395 2.18×
      cachehammer
      		 2,424,984 33,989,714 14.02×
      cacheline
      		 114.22 1,574 13.78×
      l1cache
      		 392.11 6,226 15.88×
      memcpy
      		 1,015 15,333 15.11×
      memrate
      		 6.93 30.72 4.43×
      memthrash
      		 253.75 543.57 2.14×
      ptr-chase
      		 36,753,016 212,652,223 5.79×
      spinmem
      		 4,757 14,700 3.09×
      stream
      		 120.5 8,267 68.60×
      vm
      		 201,332 1,551,562 7.71×

      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.8xlarge 32128 GiB0
      m9g.12xlarge 48192 GiB0
      m9g.16xlarge 64256 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      m9g.4xlarge FAQs