c9g.48xlarge by Amazon Web Services

c9g.48xlarge is a Compute optimized [AWS Graviton processors] Gen9 48xlarge server offered by Amazon Web Services with 192 vCPUs, 384 GiB of memory and 0 GB of storage. The pricing starts at 1.2481 USD per hour.
192 vCPU
384 GiB Memory
Spare SCore
380,394
(All-cores)
2,006
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
c9g.48xlarge
Description
Compute optimized [AWS Graviton processors] Gen9 48xlarge
Family
Compute Optimized
Series
c9g
Hw Virt
Average Time To Start
7.5
Status
active
Observed At
2026-11-14T01:02:04.731028

Availability

Region / IDSpotOndemand
(MY) / ap-southeast-5
2.55685 USD/h
8.1485 USD/h
Ohio (US) / us-east-2
1.4556 USD/h
8.3174 USD/h
Oregon (US) / us-west-2
2.5712 USD/h
8.3462 USD/h
Northern Virgina (US) / us-east-1
2.756025 USD/h
8.3462 USD/h
Seoul (KR) / ap-northeast-2
1.684267 USD/h
9.3926 USD/h
Frankfurt (DE) / eu-central-1
3.007333 USD/h
9.4906 USD/h
Singapore (SG) / ap-southeast-1
3.278667 USD/h
9.5885 USD/h
Tokyo (JP) / ap-northeast-1
2.297667 USD/h
10.4698 USD/h

Processor

vCPUs
192
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
192
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
12 MiB
CPU L1I Cache
64 KiB
CPU L1I Cache Total
12 MiB
CPU L2 Cache
2 MiB
CPU L2 Cache Total
384 MiB
CPU L3 Cache
96 MiB
CPU L3 Cache Total
192 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
189.6
Scalability
98.75

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
      Compatible Storage IDs
      standard, gp2, gp3, st1, sc1, io1, io2
      Network
      Network Speed Baseline
      100 Gbps
      Network Speed Max
      100 Gbps
      Network Storage Speed Baseline
      72 Gbps
      Network Storage Speed Max
      72 Gbps
      Inbound Traffic
      0 GB/month
      Outbound Traffic
      0 GB/month
      IPv4
      0

      CPU and System Topology

      Server Description

      High-density ARM compute instance with 192 dedicated physical cores, 100 Gbps networking, and fast memory throughput for parallel enterprise workloads.

      Amazon Web Services c9g.48xlarge is a compute-optimized instance featuring 192 dedicated physical cores and 192 vCPUs powered by AWS ARMv9 Neoverse-V3 processors running at 3.3 GHz. Configured with 384.0 GB of RAM (2.0 GB per vCPU) and a 100 Gbps network baseline, the server omits local storage and GPUs. Benchmark evaluations show top-tier multi-core compute capability, reaching 380,393.63 in stress-ng multi-core testing, alongside memory read bandwidth of 729.09 GB/sec and Redis throughput exceeding 511 million operations per second. Single-core throughput is moderate, and LLM text generation speed is constrained. The instance delivers high resource density for parallel tasks, offering efficient resource utilization where local storage is unnecessary. Best-fit workloads include distributed caching, high-concurrency web serving, parallel batch processing, and database operations.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      15Score
      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) 62,484,025 ops/sec 1,933,252 ops/sec 33 50.00% 50.00% +470.00%
      Redis RPS (pipeline=16, SET) 373,347,930 ops/sec 11,814,424 ops/sec 31 20.00% 20.00% +99.00%
      PassMark Memory Mark (composite) 4,605 2,408 1.9 10.00% 10.00% +6.60%
      Memory bandwidth (read, 16 MB ~ L3) 850,616 MB/sec 108,674 MB/sec 7.7 10.00% 10.00% +23.00%
      PassMark single-thread CPU 2,458 Mops/s 2,365 Mops/s 1 10.00% 10.00% 0.00%

      Memory Bandwidth

      Compression

      OpenSSL

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 106,963
      Compression
      		 1,753,696
      Encryption
      		 55,958
      Extended Instructions
      		 242,398
      Floating Point Maths
      		 1,449,530
      Integer Maths
      		 1,161,357
      Physics
      		 42,526
      Prime Numbers
      		 2,221
      Single Threaded
      		 2,458
      String Sorting
      		 953,344

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 4,605
      Database Operations
      		 61,798
      Memory Latency
      		 29
      Memory Read Cached
      		 24,848
      Memory Read Uncached
      		 24,465
      Memory Write
      		 24,997

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 120.17 - -
      bitops
      		 117,248 12,246,146 104.45×
      branch
      		 320,251 26,566,213 82.95×
      funccall
      		 2,279 430,751 188.97×
      funcret
      		 40,791 7,071,897 173.37×
      hash
      		 181,258 34,102,641 188.14×
      intmath
      		 39,542 7,478,842 189.14×
      nop
      		 429,515 81,427,557 189.58×
      prime
      		 600,104 112,154,769 186.89×
      rotate
      		 148,768 28,178,246 189.41×
      str
      		 933,993 174,043,998 186.34×
      wcs
      		 280,645 52,773,387 188.04×
      CryptographySingleMultiScaling
      crypt
      		 4,292 801,620 186.76×
      CompressionSingleMultiScaling
      jpeg
      		 913.83 110,275 120.67×
      zlib
      		 33.18 9,123 274.96×
      HypervisorSingleMultiScaling
      clock
      		 39,536 137,031 3.47×
      clone
      		 323.14 25,764 79.73×
      context
      		 3,953 752,854 190.46×
      cpu-sched
      		 69.85 9,991 143.04×
      eventfd
      		 150,224 4,244,650 28.26×
      fault
      		 27,765 273,294 9.84×
      fork
      		 5,187 67,547 13.02×
      getrandom
      		 73,958 14,049,396 189.96×
      hrtimers
      		 433,637 8,015,697 18.48×
      mprotect
      		 813,823 16,443,811 20.21×
      mtx
      		 12,881,423 10,396,757,330 807.11×
      munmap
      		 3,897 89,906 23.07×
      null
      		 682,202 130,015,712 190.58×
      pipe
      		 972,709 82,385,993 84.70×
      priv-instr
      		 1,117,264 8,014,331 7.17×
      resched
      		 1,130,217 29,061,163 25.71×
      switch
      		 255,531 59,199,899 231.67×
      timermix
      		 588,176 35,555,036 60.45×
      tlb-shootdown
      		 16,146 212,440 13.16×
      vdso
      		 64,200,851 11,219,711,596 174.76×
      vfork
      		 39,298 263,974 6.72×
      yield
      		 355,076,407 352,977,300 0.99×
      zero
      		 3,352,987 621,297,879 185.30×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 2,243 424,919 189.47×
      expmath
      		 424.83 80,128 188.61×
      fma
      		 852,244 161,859,191 189.92×
      fp
      		 174.74 33,293 190.53×
      fractal
      		 9.2 1,701 184.85×
      hyperbolic
      		 407.97 77,513 190.00×
      logmath
      		 490.88 93,322 190.11×
      matrix
      		 7,978 1,493,704 187.23×
      matrix-3d
      		 1,481 35,351 23.87×
      monte-carlo
      		 269.6 51,583 191.33×
      mpfr
      		 1,883 352,878 187.43×
      powmath
      		 281.81 53,004 188.09×
      trig
      		 553.08 104,169 188.34×
      veccmp
      		 26,331 5,001,726 189.95×
      vecfp
      		 1,859 348,152 187.26×
      vecmath
      		 4,812 914,188 189.98×
      vecshuf
      		 1,029 195,138 189.62×
      vecwide
      		 30,126 5,634,897 187.04×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 11.2 801.31 71.55×
      bsearch
      		 422.03 80,225 190.09×
      bubblesort
      		 1.4 268.8 192.00×
      fibsearch
      		 413.78 77,956 188.40×
      heapsort
      		 15.4 2,881 187.09×
      hsearch
      		 10,834 2,037,817 188.09×
      insertionsort
      		 7.8 1,489 190.87×
      malloc
      		 4,129,391 296,214,006 71.73×
      mcontend
      		 167.08 490,287 2934.45×
      mergesort
      		 38.6 7,228 187.25×
      qsort
      		 26.8 5,011 186.97×
      skiplist
      		 7,646 1,454,101 190.17×
      tree
      		 2 191.13 95.56×
      MemorySingleMultiScaling
      cache
      		 588,780 7,555,687 12.83×
      cachehammer
      		 2,165,894 19,740,864 9.11×
      cacheline
      		 60.16 4,560 75.79×
      l1cache
      		 389.36 60,231 154.69×
      memcpy
      		 1,017 173,151 170.23×
      memrate
      		 6.93 95.51 13.78×
      memthrash
      		 512.55 343.11 0.67×
      ptr-chase
      		 26,798,546 1,723,860,779 64.33×
      spinmem
      		 4,847 172,547 35.60×
      stream
      		 26.81 241,696 9015.15×
      vm
      		 197,349 5,232,805 26.52×

      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.48xlarge FAQs