c9g.12xlarge by Amazon Web Services

c9g.12xlarge is a Compute optimized [AWS Graviton processors] Gen9 12xlarge server offered by Amazon Web Services with 48 vCPUs, 96 GiB of memory and 0 GB of storage. The pricing starts at 0.4582 USD per hour.
48 vCPU
96 GiB Memory
Spare SCore
96,125
(All-cores)
2,010
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
c9g.12xlarge
Description
Compute optimized [AWS Graviton processors] Gen9 12xlarge
Family
Compute Optimized
Series
c9g
Hw Virt
Average Time To Start
6.67
Status
active
Observed At
2026-11-14T19:09:28.103439

Availability

Region / IDSpotOndemand
(MY) / ap-southeast-5
0.95065 USD/h
2.0371 USD/h
Ohio (US) / us-east-2
0.569 USD/h
2.0794 USD/h
Northern Virgina (US) / us-east-1
0.6087 USD/h
2.0866 USD/h
Oregon (US) / us-west-2
0.862575 USD/h
2.0866 USD/h
Seoul (KR) / ap-northeast-2
0.602667 USD/h
2.3482 USD/h
Frankfurt (DE) / eu-central-1
1.011633 USD/h
2.3726 USD/h
Singapore (SG) / ap-southeast-1
0.979967 USD/h
2.3971 USD/h
Tokyo (JP) / ap-northeast-1
1.0295 USD/h
2.6174 USD/h

Processor

vCPUs
48
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
48
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
3 MiB
CPU L1I Cache
64 KiB
CPU L1I Cache Total
3 MiB
CPU L2 Cache
2 MiB
CPU L2 Cache Total
96 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
47.8
Scalability
99.58

System Resources and Accelerators

Memory
Memory Amount
96 GiB
Memory Amount Actual
95 GiB
Accelerators
Accelerator Count
0
Accelerator Memory Min
0 MiB
Accelerator Memory Total
0 MiB
Accelerators
    Storage
    Storage Size
    0 GB
    Storages
      Compatible Storage IDs
      standard, gp2, gp3, st1, sc1, io1, io2
      Network
      Network Speed Baseline
      25 Gbps
      Network Speed Max
      25 Gbps
      Network Storage Speed Baseline
      18 Gbps
      Network Storage Speed Max
      18 Gbps
      Inbound Traffic
      0 GB/month
      Outbound Traffic
      0 GB/month
      IPv4
      0

      CPU and System Topology

      Server Description

      An arm64 compute-optimized instance delivering 48 dedicated physical cores, high compilation speed, and exceptional key-value operational throughput for compute-heavy workloads.

      Amazon Web Services c9g.12xlarge is a compute-optimized instance driven by 48 dedicated physical cores on 64-bit ARMv9 AWS Graviton Neoverse-V3 processors running at 3.3 GHz. Operating on the AWS Nitro hypervisor, the instance pairs 48 vCPUs with 96.0 GB of RAM, yielding a 2.0 GB per vCPU ratio. It excludes local NVMe storage and discrete GPUs, relying on a 25 Gbps baseline network bandwidth. Benchmark evaluations highlight top-tier results in single-core and multi-core Geekbench tests, software compilation, static web serving throughput reaching 103.35 GB/sec, and Redis SET operations exceeding 136 million ops/sec. Memory performance is supported by 48 MB of L3 cache and a high PassMark memory score. The server offers clear cost efficiency for parallel CPU workloads without requiring extensive memory overhead, making it well suited for continuous integration, code compilation, high-throughput web serving, and database cache operations.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      5.2Score
      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) 16,975,672 ops/sec 1,933,252 ops/sec 8.9 50.00% 50.00% +200.00%
      Redis RPS (pipeline=16, SET) 99,090,988 ops/sec 11,814,424 ops/sec 8.2 20.00% 20.00% +52.00%
      PassMark Memory Mark (composite) 4,685 2,408 2 10.00% 10.00% +7.20%
      Memory bandwidth (read, 16 MB ~ L3) 221,604 MB/sec 108,674 MB/sec 2 10.00% 10.00% +7.20%
      PassMark single-thread CPU 2,468 Mops/s 2,365 Mops/s 1 10.00% 10.00% 0.00%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 2,387

      Geekbench Multi-Core

      Score: 28,306

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 49,501
      Compression
      		 448,182
      Encryption
      		 14,330
      Extended Instructions
      		 64,651
      Floating Point Maths
      		 367,089
      Integer Maths
      		 293,662
      Physics
      		 11,434
      Prime Numbers
      		 596
      Single Threaded
      		 2,468
      String Sorting
      		 250,311

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 4,685
      Database Operations
      		 47,371
      Memory Latency
      		 26
      Memory Read Cached
      		 24,866
      Memory Read Uncached
      		 24,698
      Memory Write
      		 25,061

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 169.37 19.33 0.11×
      bitops
      		 165,345 7,923,257 47.92×
      branch
      		 320,452 15,334,885 47.85×
      funccall
      		 2,283 109,217 47.84×
      funcret
      		 41,231 1,888,660 45.81×
      hash
      		 181,569 8,685,157 47.83×
      intmath
      		 39,633 1,899,898 47.94×
      nop
      		 430,337 20,581,559 47.83×
      prime
      		 600,820 28,785,770 47.91×
      rotate
      		 149,222 7,130,597 47.79×
      str
      		 935,532 44,727,101 47.81×
      wcs
      		 281,252 13,343,581 47.44×
      CryptographySingleMultiScaling
      crypt
      		 4,292 205,671 47.91×
      CompressionSingleMultiScaling
      jpeg
      		 920.43 43,398 47.15×
      zlib
      		 63.64 2,285 35.90×
      HypervisorSingleMultiScaling
      clock
      		 51,184 502,393 9.82×
      clone
      		 395.81 10,248 25.89×
      context
      		 3,959 192,105 48.53×
      cpu-sched
      		 59.85 3,088 51.60×
      eventfd
      		 149,979 3,146,536 20.98×
      fault
      		 25,930 472,758 18.23×
      fork
      		 7,088 72,936 10.29×
      getrandom
      		 73,978 3,545,033 47.92×
      hrtimers
      		 776,601 6,712,229 8.64×
      mprotect
      		 1,409,302 23,412,913 16.61×
      mtx
      		 10,079,437 2,700,656,301 267.94×
      munmap
      		 5,225 113,233 21.67×
      null
      		 684,898 33,163,899 48.42×
      pipe
      		 1,369,452 33,762,671 24.65×
      priv-instr
      		 1,134,048 13,955,643 12.31×
      resched
      		 3,155,648 8,848,703 2.80×
      switch
      		 248,637 33,498,290 134.73×
      timermix
      		 592,114 16,827,846 28.42×
      tlb-shootdown
      		 21,256 276,450 13.01×
      vdso
      		 64,311,459 3,059,334,616 47.57×
      vfork
      		 60,834 479,531 7.88×
      yield
      		 80,313,653 97,533,734 1.21×
      zero
      		 3,280,794 157,822,683 48.11×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 2,247 107,081 47.65×
      expmath
      		 425.42 20,360 47.86×
      fma
      		 853,553 40,874,614 47.89×
      fp
      		 175.2 8,455 48.26×
      fractal
      		 9.2 434.26 47.20×
      hyperbolic
      		 408.66 19,543 47.82×
      logmath
      		 491.88 23,526 47.83×
      matrix
      		 8,001 382,684 47.83×
      matrix-3d
      		 1,494 9,128 6.11×
      monte-carlo
      		 269.67 13,061 48.43×
      mpfr
      		 1,888 90,316 47.84×
      powmath
      		 282.33 13,492 47.79×
      trig
      		 553.86 26,501 47.85×
      veccmp
      		 26,372 1,260,924 47.81×
      vecfp
      		 1,862 88,951 47.78×
      vecmath
      		 4,819 230,415 47.82×
      vecshuf
      		 1,030 49,157 47.73×
      vecwide
      		 32,411 1,442,671 44.51×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 11.2 537.59 48.00×
      bsearch
      		 423.5 20,245 47.80×
      bubblesort
      		 1.4 67.2 48.00×
      fibsearch
      		 413.51 19,832 47.96×
      heapsort
      		 15.4 738.59 47.96×
      hsearch
      		 10,817 520,360 48.11×
      insertionsort
      		 8 376.4 47.05×
      malloc
      		 4,603,489 121,209,278 26.33×
      mcontend
      		 289.74 116,797 403.11×
      mergesort
      		 38.6 1,852 47.99×
      qsort
      		 26.8 1,285 47.95×
      skiplist
      		 7,678 366,856 47.78×
      tree
      		 2.2 48.32 21.96×
      MemorySingleMultiScaling
      cache
      		 699,858 1,133,622 1.62×
      cachehammer
      		 2,371,287 56,050,033 23.64×
      cacheline
      		 48.77 6,520 133.68×
      l1cache
      		 390.07 18,518 47.47×
      memcpy
      		 1,015 45,891 45.22×
      memrate
      		 6.52 34.15 5.24×
      memthrash
      		 366.02 690.88 1.89×
      ptr-chase
      		 35,457,857 459,001,304 12.94×
      spinmem
      		 4,481 60,539 13.51×
      stream
      		 108.61 71,544 658.72×
      vm
      		 196,850 3,768,520 19.14×

      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
      c6g.medium 12 GiB0
      c6gd.medium 12 GiB0
      c6gn.medium 12 GiB0
      c7a.medium 12 GiB0
      c7g.medium 12 GiB0
      c7gd.medium 12 GiB0
      c7gn.medium 12 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      c9g.12xlarge FAQs