c8a.12xlarge by Amazon Web Services

c8a.12xlarge is a Compute optimized [AMD processors] Gen8 12xlarge server offered by Amazon Web Services with 48 vCPUs, 96 GiB of memory and 0 GB of storage. The pricing starts at 0.2775 USD per hour.
48 vCPU
96 GiB Memory
Spare SCore
179,310
(All-cores)
3,779
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
c8a.12xlarge
Description
Compute optimized [AMD processors] Gen8 12xlarge
Family
c8a
Hw Virt
Average Time To Start
7.5
Status
active
Observed At
2026-10-29T10:04:49.302824

Availability

REGION / IDSPOTONDEMAND
Ohio (US) / us-east-2
1.0436 USD/h 2.5865 USD/h
Oregon (US) / us-west-2
1.011075 USD/h 2.5865 USD/h
Northern Virgina (US) / us-east-1
1.11684 USD/h 2.5865 USD/h
Aragón (ES) / eu-south-2
0.405367 USD/h 2.7746 USD/h
Dublin (IE) / eu-west-1
1.13965 USD/h 2.7751 USD/h
Frankfurt (DE) / eu-central-1
1.009467 USD/h 2.9518 USD/h
Tokyo (JP) / ap-northeast-1
1.085467 USD/h 3.2558 USD/h

Processor

vCPUs
48
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
48
CPU Speed
4.5 GHz
CPU Architecture
x86_64
CPU Manufacturer
AMD
CPU Family
EPYC
CPU Model
9R45
CPU L1D Cache
48 KiB
CPU L1D Cache Total
2 MiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
2 MiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
48 MiB
CPU L3 Cache
32 MiB
CPU L3 Cache Total
192 MiB
CPU Flags
fpu, vme, de, pse, tsc, msr, pae, mce, cx8, apic, sep, mtrr, pge, mca, cmov, pat, pse36, clflush, mmx, fxsr, sse, sse2, ht, syscall, nx, mmxext, fxsr_opt, pdpe1gb, rdtscp, lm, constant_tsc, rep_good, nopl, xtopology, nonstop_tsc, cpuid, extd_apicid, aperfmperf, tsc_known_freq, pni, pclmulqdq, monitor, ssse3, fma, cx16, pcid, sse4_1, sse4_2, x2apic, movbe, popcnt, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, cmp_legacy, cr8_legacy, abm, sse4a, misalignsse, 3dnowprefetch, topoext, perfctr_core, ssbd, perfmon_v2, ibrs, ibpb, stibp, ibrs_enhanced, vmmcall, fsgsbase, tsc_adjust, bmi1, avx2, smep, bmi2, erms, invpcid, avx512f, avx512dq, rdseed, adx, smap, avx512ifma, clflushopt, clwb, avx512cd, sha_ni, avx512bw, avx512vl, xsaveopt, xsavec, xgetbv1, xsaves, avx_vnni, avx512_bf16, clzero, xsaveerptr, rdpru, wbnoinvd, arat, avx512vbmi, pku, ospke, avx512_vbmi2, gfni, vaes, vpclmulqdq, avx512_vnni, avx512_bitalg, avx512_vpopcntdq, rdpid, movdiri, movdir64b, fsrm, avx512_vp2intersect, flush_l1d
Ecpus
47.4
Scalability
98.75

System Resources and Accelerators

MEMORY
Memory Amount
96 GiB
Memory Amount Actual
96 GiB
Memory Generation
DDR5
Memory Speed
6400 Mhz
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
      22.5 Gbps
      Network Speed Max
      22.5 Gbps
      Network Storage Speed Baseline
      15 Gbps
      Network Storage Speed Max
      15 Gbps
      Inbound Traffic
      0 GB/month
      Outbound Traffic
      0 GB/month
      IPv4
      0

      CPU and System Topology

      Server Description

      A dedicated 48-core AMD EPYC compute-optimized server with DDR5 memory, engineered for high-throughput processing and compute-intensive workloads.

      Compute Optimized

      Amazon Web Services c8a.12xlarge is an x86_64 compute-optimized server featuring 48 dedicated physical cores and 48 vCPUs powered by an AMD EPYC 9R45 processor running at 4.5 GHz. It includes 96.0 GB of DDR5 memory at 6 GHz, providing a resource density of 2.0 GB per core, but lacks local storage and GPU accelerators. Built on the Nitro hypervisor, it delivers 22 Gbps baseline network bandwidth. Benchmark data places this instance in the top tier (top 10%) for single-core and multi-core CPU execution, software compilation, and database operations. The low memory-to-core ratio and lack of local storage represent a tradeoff, making it highly cost-efficient for compute-heavy, non-storage-intensive workloads. It is suited for tasks such as software compilation, batch processing, and CPU-based inference.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      5.6Score
      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) 16,662,025 ops/sec 1,919,289 ops/sec 8.9 50.00% 50.00% +200.00%
      Redis RPS (pipeline=16, SET) 107,560,740 ops/sec 11,728,058 ops/sec 9.2 20.00% 20.00% +56.00%
      PassMark Memory Mark (composite) 2,908 2,416 1.2 10.00% 10.00% +1.80%
      Memory bandwidth (read, 16 MB ~ L3) 357,838 MB/sec 108,466 MB/sec 3.3 10.00% 10.00% +13.00%
      PassMark single-thread CPU 3,815 Mops/s 2,365 Mops/s 1.6 10.00% 10.00% +4.80%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 2,818

      Geekbench Multi-Core

      Score: 29,814

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 102,416
      Compression
      		 1,479,296
      Encryption
      		 75,619
      Extended Instructions
      		 129,410
      Floating Point Maths
      		 364,394
      Integer Maths
      		 363,086
      Physics
      		 17,020
      Prime Numbers
      		 1,284
      Single Threaded
      		 3,815
      String Sorting
      		 204,308

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2,908
      Database Operations
      		 41,380
      Memory Latency
      		 82
      Memory Read Cached
      		 33,961
      Memory Read Uncached
      		 32,540
      Memory Write
      		 32,734

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 517.98 338.87 0.65×
      bitops
      		 233,295 10,842,445 46.48×
      branch
      		 184,911 8,582,071 46.41×
      funccall
      		 909.27 40,663 44.72×
      funcret
      		 26,882 1,227,753 45.67×
      hash
      		 219,448 10,169,939 46.34×
      intmath
      		 80,325 3,778,070 47.03×
      nop
      		 433,591 20,080,071 46.31×
      prime
      		 626,186 27,371,528 43.71×
      rotate
      		 142,782 6,701,872 46.94×
      str
      		 1,658,587 67,324,719 40.59×
      wcs
      		 1,047,660 42,040,877 40.13×
      CryptographySingleMultiScaling
      crypt
      		 5,451 233,373 42.81×
      CompressionSingleMultiScaling
      jpeg
      		 1,285 55,998 43.56×
      zlib
      		 78.82 3,409 43.25×
      HypervisorSingleMultiScaling
      clock
      		 49,258 367,378 7.46×
      clone
      		 301.37 9,576 31.77×
      context
      		 9,245 432,804 46.81×
      cpu-sched
      		 62.43 3,149 50.44×
      eventfd
      		 150,885 7,922,604 52.51×
      fault
      		 44,506 225,984 5.08×
      fork
      		 6,768 127,697 18.87×
      getrandom
      		 101,027 4,554,856 45.09×
      hrtimers
      		 167,109 2,907,282 17.40×
      mprotect
      		 720,507 23,154,775 32.14×
      mtx
      		 45,178,722 4,023,922,735 89.07×
      munmap
      		 5,532 126,924 22.95×
      null
      		 1,558,738 71,820,783 46.08×
      pipe
      		 3,104,101 39,515,424 12.73×
      priv-instr
      		 1,613,648 22,946,266 14.22×
      resched
      		 16,179,206 14,842,691 0.92×
      switch
      		 362,651 30,908,331 85.23×
      timermix
      		 512,131 23,895,642 46.66×
      tlb-shootdown
      		 18,695 279,468 14.95×
      tsc
      		 889,180 41,701,859 46.90×
      usersyscall
      		 1,152,828 23,042,570 19.99×
      vdso
      		 109,404,655 5,122,739,226 46.82×
      vfork
      		 41,073 220,078 5.36×
      x86syscall
      		 19,902,044 925,903,308 46.52×
      yield
      		 84,318,938 101,637,640 1.21×
      zero
      		 10,704,413 479,249,562 44.77×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 17,622 811,663 46.06×
      expmath
      		 4,025 186,298 46.29×
      fma
      		 1,573,009 70,863,782 45.05×
      fp
      		 212.47 9,583 45.10×
      fractal
      		 9 413.77 45.97×
      hyperbolic
      		 5,509 256,924 46.64×
      logmath
      		 5,746 268,300 46.70×
      matrix
      		 8,939 369,805 41.37×
      matrix-3d
      		 1,607 13,144 8.18×
      monte-carlo
      		 442.73 21,122 47.71×
      mpfr
      		 2,448 106,013 43.30×
      powmath
      		 1,850 85,627 46.28×
      trig
      		 2,448 113,148 46.22×
      veccmp
      		 30,354 1,344,131 44.28×
      vecfp
      		 2,421 112,756 46.57×
      vecmath
      		 4,786 222,042 46.39×
      vecshuf
      		 1,006 45,376 45.11×
      vecwide
      		 40,449 1,720,485 42.53×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 12.8 572.41 44.72×
      bsearch
      		 367.79 16,442 44.70×
      bubblesort
      		 1.2 48.2 40.17×
      fibsearch
      		 433.24 19,877 45.88×
      heapsort
      		 14.4 626.59 43.51×
      hsearch
      		 13,831 570,019 41.21×
      insertionsort
      		 9.6 534.41 55.67×
      malloc
      		 5,452,383 106,351,285 19.51×
      mcontend
      		 120.12 8,755 72.88×
      mergesort
      		 39 1,720 44.11×
      qsort
      		 27 1,190 44.07×
      skiplist
      		 8,487 388,167 45.74×
      tree
      		 2.6 78.16 30.06×
      MemorySingleMultiScaling
      cache
      		 1,181,978 1,585,606 1.34×
      cachehammer
      		 272,815 11,613,645 42.57×
      cacheline
      		 58.18 4,438 76.27×
      l1cache
      		 1,382 63,048 45.61×
      memcpy
      		 813.29 36,387 44.74×
      memrate
      		 0.99 18.54 18.73×
      memthrash
      		 258.9 2,347 9.07×
      ptr-chase
      		 77,581,516 458,205,726 5.91×
      spinmem
      		 297.19 3,339 11.24×
      stream
      		 161.49 62,089 384.48×
      vm
      		 241,773 298,409 1.23×

      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
      c8a.medium 12 GiB0
      c8a.large 24 GiB0
      c8a.xlarge 48 GiB0
      c8a.2xlarge 816 GiB0
      c8a.4xlarge 1632 GiB0
      c8a.8xlarge 3264 GiB0
      c8a.16xlarge 64128 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      c8a.12xlarge FAQs