m9g.8xlarge by Amazon Web Services

m9g.8xlarge is a General purpose [AWS Graviton processors] Gen9 8xlarge server offered by Amazon Web Services with 32 vCPUs, 128 GiB of memory and 0 GB of storage. The pricing starts at 0.2686 USD per hour.
32 vCPU
128 GiB Memory
Spare SCore
64,161
(All-cores)
2,009
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
m9g.8xlarge
Description
General purpose [AWS Graviton processors] Gen9 8xlarge
Family
m9g
Hw Virt
Average Time To Start
12
Status
active
Observed At
2026-10-28T19:56:30.297505

Availability

REGION / IDSPOTONDEMAND
Northern Virgina (US) / us-east-1
0.5295 USD/h 1.5654 USD/h
Ohio (US) / us-east-2
0.530567 USD/h 1.5654 USD/h
Oregon (US) / us-west-2
0.6163 USD/h 1.5654 USD/h
(MY) / ap-southeast-5
0.5491 USD/h 1.6634 USD/h
Aragón (ES) / eu-south-2
0.2696 USD/h 1.7437 USD/h
Dublin (IE) / eu-west-1
0.899367 USD/h 1.7446 USD/h
Frankfurt (DE) / eu-central-1
0.768133 USD/h 1.8755 USD/h
Sydney (AU) / ap-southeast-2
0.744 USD/h 1.9568 USD/h
Singapore (SG) / ap-southeast-1
0.8549 USD/h 1.9568 USD/h
Tokyo (JP) / ap-northeast-1
0.808933 USD/h 2.0221 USD/h

Processor

vCPUs
32
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
32
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
2 MiB
CPU L1I Cache
64 KiB
CPU L1I Cache Total
2 MiB
CPU L2 Cache
2 MiB
CPU L2 Cache Total
64 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
31.9
Scalability
99.69

System Resources and Accelerators

MEMORY
Memory Amount
128 GiB
Memory Amount Actual
126 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
      17 Gbps
      Network Speed Max
      17 Gbps
      Network Storage Speed Baseline
      12 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 ARMv9-powered general-purpose instance delivering top-tier database performance, software compilation, and high memory bandwidth across thirty-two dedicated cores.

      General Purpose

      Amazon Web Services m9g.8xlarge is a general-purpose instance powered by a 3.3 GHz AWS Graviton Gen9 processor built on the ARMv9 Neoverse-V3 architecture. It features 32 dedicated physical cores, 128.0 GB of RAM, and a 17 Gbps baseline network speed, running on the Nitro hypervisor. The instance lacks local storage and GPU accelerators. Performance benchmarks show top-tier capabilities in software compilation, database operations, static web serving, and single-threaded compression, alongside strong multi-core processing. However, LLM text generation performance is relatively weak. This instance offers a highly resource-dense, cost-efficient profile for general-purpose workloads, making it suitable for multi-threaded applications, web serving, and database management.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      3.8Score
      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) 11,272,071 ops/sec 1,919,289 ops/sec 5.8 50.00% 50.00% +140.00%
      Redis RPS (pipeline=16, SET) 65,561,762 ops/sec 11,728,058 ops/sec 5.5 20.00% 20.00% +41.00%
      PassMark Memory Mark (composite) 4,531 2,416 1.9 10.00% 10.00% +6.60%
      Memory bandwidth (read, 16 MB ~ L3) 196,315 MB/sec 108,466 MB/sec 1.8 10.00% 10.00% +6.10%
      PassMark single-thread CPU 2,463 Mops/s 2,365 Mops/s 1 10.00% 10.00% 0.00%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 2,390

      Geekbench Multi-Core

      Score: 25,914

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 36,704
      Compression
      		 298,978
      Encryption
      		 9,559
      Extended Instructions
      		 43,114
      Floating Point Maths
      		 244,850
      Integer Maths
      		 195,899
      Physics
      		 9,391
      Prime Numbers
      		 558
      Single Threaded
      		 2,463
      String Sorting
      		 170,220

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 4,531
      Database Operations
      		 45,926
      Memory Latency
      		 27
      Memory Read Cached
      		 24,144
      Memory Read Uncached
      		 24,478
      Memory Write
      		 24,999

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 150.52 37.8 0.25×
      bitops
      		 164,945 5,279,062 32.01×
      branch
      		 319,979 10,231,002 31.97×
      funccall
      		 2,280 72,865 31.96×
      funcret
      		 40,626 1,253,755 30.86×
      hash
      		 181,245 5,791,669 31.95×
      intmath
      		 39,555 1,263,467 31.94×
      nop
      		 429,614 13,733,173 31.97×
      prime
      		 600,545 19,210,975 31.99×
      rotate
      		 149,050 4,761,876 31.95×
      str
      		 936,642 29,947,019 31.97×
      wcs
      		 278,995 8,926,013 31.99×
      CryptographySingleMultiScaling
      crypt
      		 4,292 137,126 31.95×
      CompressionSingleMultiScaling
      jpeg
      		 905.73 28,797 31.79×
      zlib
      		 39.39 1,479 37.54×
      HypervisorSingleMultiScaling
      clock
      		 53,161 616,941 11.61×
      clone
      		 402.71 7,124 17.69×
      context
      		 4,259 129,461 30.40×
      cpu-sched
      		 60.21 2,024 33.61×
      eventfd
      		 165,174 2,539,176 15.37×
      fault
      		 27,371 358,220 13.09×
      fork
      		 6,835 51,204 7.49×
      getrandom
      		 73,982 2,365,269 31.97×
      hrtimers
      		 256,774 5,828,536 22.70×
      mprotect
      		 1,573,619 17,374,428 11.04×
      mtx
      		 10,474,957 1,627,458,681 155.37×
      munmap
      		 5,394 106,437 19.73×
      null
      		 682,167 22,257,612 32.63×
      pipe
      		 1,382,188 26,052,686 18.85×
      priv-instr
      		 1,117,791 14,348,776 12.84×
      resched
      		 3,248,726 7,624,250 2.35×
      switch
      		 295,088 22,374,785 75.82×
      timermix
      		 595,166 17,728,671 29.79×
      tlb-shootdown
      		 21,195 244,638 11.54×
      vdso
      		 64,098,075 1,988,329,229 31.02×
      vfork
      		 64,198 493,436 7.69×
      yield
      		 54,379,138 65,123,897 1.20×
      zero
      		 3,256,550 104,921,307 32.22×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 2,241 71,670 31.98×
      expmath
      		 425 13,581 31.96×
      fma
      		 853,554 27,269,742 31.95×
      fp
      		 177.6 5,617 31.63×
      fractal
      		 9.2 290.03 31.52×
      hyperbolic
      		 408.12 13,043 31.96×
      logmath
      		 490.98 15,690 31.96×
      matrix
      		 7,967 254,568 31.95×
      matrix-3d
      		 1,506 8,529 5.66×
      monte-carlo
      		 269.64 8,739 32.41×
      mpfr
      		 1,888 60,315 31.95×
      powmath
      		 281.97 9,014 31.97×
      trig
      		 553.32 17,679 31.95×
      veccmp
      		 26,313 840,954 31.96×
      vecfp
      		 1,858 59,388 31.96×
      vecmath
      		 4,822 153,641 31.86×
      vecshuf
      		 1,027 32,899 32.03×
      vecwide
      		 32,376 1,035,257 31.98×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 11.2 358.59 32.02×
      bsearch
      		 421.96 13,480 31.95×
      bubblesort
      		 1.4 44.8 32.00×
      fibsearch
      		 413.48 13,221 31.98×
      heapsort
      		 15.4 492.19 31.96×
      hsearch
      		 10,821 346,282 32.00×
      insertionsort
      		 7.4 244 32.97×
      malloc
      		 4,631,396 86,986,857 18.78×
      mcontend
      		 287.28 77,154 268.57×
      mergesort
      		 38.8 1,236 31.86×
      qsort
      		 26.8 857.18 31.98×
      skiplist
      		 7,663 244,953 31.97×
      tree
      		 2.2 39.55 17.98×
      MemorySingleMultiScaling
      cache
      		 711,373 1,089,972 1.53×
      cachehammer
      		 2,422,610 52,987,732 21.87×
      cacheline
      		 76.93 4,395 57.13×
      l1cache
      		 390.8 12,450 31.86×
      memcpy
      		 1,016 30,693 30.22×
      memrate
      		 6.72 30.76 4.58×
      memthrash
      		 309.31 828.49 2.68×
      ptr-chase
      		 34,294,151 360,537,324 10.51×
      spinmem
      		 4,175 31,433 7.53×
      stream
      		 102.93 26,974 262.06×
      vm
      		 201,269 2,857,889 14.20×

      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.12xlarge 48192 GiB0
      m9g.16xlarge 64256 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      m9g.8xlarge FAQs