c8a.48xlarge by Amazon Web Services

c8a.48xlarge is a Compute optimized [AMD processors] Gen8 48xlarge server offered by Amazon Web Services with 192 vCPUs, 384 GiB of memory and 0 GB of storage. The pricing starts at 1.1099 USD per hour.
192 vCPU
384 GiB Memory
Spare SCore
683,823
(All-cores)
3,793
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
c8a.48xlarge
Description
Compute optimized [AMD processors] Gen8 48xlarge
Family
c8a
Hw Virt
Average Time To Start
7
Status
active
Observed At
2026-10-30T22:24:57.729843

Availability

REGION / IDSPOTONDEMAND
Northern Virgina (US) / us-east-1
4.03592 USD/h 10.3459 USD/h
Oregon (US) / us-west-2
4.00565 USD/h 10.3459 USD/h
Ohio (US) / us-east-2
5.4787 USD/h 10.3459 USD/h
Aragón (ES) / eu-south-2
2.396267 USD/h 11.0986 USD/h
Dublin (IE) / eu-west-1
3.38705 USD/h 11.1005 USD/h
Frankfurt (DE) / eu-central-1
6.3433 USD/h 11.807 USD/h
Tokyo (JP) / ap-northeast-1
4.700433 USD/h 13.0234 USD/h

Processor

vCPUs
192
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
192
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
9 MiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
6 MiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
192 MiB
CPU L3 Cache
32 MiB
CPU L3 Cache Total
768 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
180.3
Scalability
93.91

System Resources and Accelerators

MEMORY
Memory Amount
384 GiB
Memory Amount Actual
384 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
      75 Gbps
      Network Speed Max
      75 Gbps
      Network Storage Speed Baseline
      60 Gbps
      Network Storage Speed Max
      60 Gbps
      Inbound Traffic
      0 GB/month
      Outbound Traffic
      0 GB/month
      IPv4
      0

      CPU and System Topology

      Server Description

      A high-density compute instance featuring 192 dedicated AMD EPYC cores, DDR5 memory, and top-tier processing performance for intensive workloads.

      Compute Optimized

      Amazon Web Services c8a.48xlarge is an x86_64 compute-optimized server instance featuring 192 dedicated physical cores and 192 vCPUs powered by an AMD EPYC 9R45 processor running at 4.5 GHz. It includes 384.0 GB of DDR5 memory at 6 GHz, providing 2.0 GB of RAM per core, and operates on the AWS Nitro hypervisor with a baseline network bandwidth of 75 Gbps. The instance lacks local storage and GPU accelerators. Benchmark results place its single-core and multi-core CPU performance, memory bandwidth, and software compilation capabilities in the top tier (top 10%). While prompt processing for large language models ranks in the top tier, text generation performance ranges from average to strong. This instance is configured for compute-intensive workloads such as software compilation, cryptography, static web serving, and high-throughput batch processing where high CPU density is required.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      13Score
      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) 48,998,277 ops/sec 1,918,343 ops/sec 26 50.00% 50.00% +410.00%
      Redis RPS (pipeline=16, SET) 315,647,596 ops/sec 11,704,734 ops/sec 27 20.00% 20.00% +93.00%
      PassMark Memory Mark (composite) 2,955 2,416 1.2 10.00% 10.00% +1.80%
      Memory bandwidth (read, 16 MB ~ L3) 1,301,012 MB/sec 108,466 MB/sec 12 10.00% 10.00% +28.00%
      PassMark single-thread CPU 3,816 Mops/s 2,365 Mops/s 1.6 10.00% 10.00% +4.80%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 2,816

      Geekbench Multi-Core

      Score: 27,743

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 183,733
      Compression
      		 4,690,875
      Encryption
      		 266,150
      Extended Instructions
      		 394,976
      Floating Point Maths
      		 1,258,390
      Integer Maths
      		 1,377,872
      Physics
      		 56,379
      Prime Numbers
      		 4,143
      Single Threaded
      		 3,816
      String Sorting
      		 620,846

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2,955
      Database Operations
      		 46,747
      Memory Latency
      		 82
      Memory Read Cached
      		 33,824
      Memory Read Uncached
      		 32,778
      Memory Write
      		 32,766

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 477.32 315.43 0.66×
      bitops
      		 231,739 36,090,068 155.74×
      branch
      		 184,727 30,478,983 164.99×
      funccall
      		 906.3 137,343 151.54×
      funcret
      		 26,784 4,046,875 151.09×
      hash
      		 217,475 36,513,761 167.90×
      intmath
      		 80,303 14,194,459 176.76×
      nop
      		 429,847 78,025,361 181.52×
      prime
      		 628,023 88,988,376 141.70×
      rotate
      		 142,479 24,791,328 174.00×
      str
      		 1,612,923 198,633,129 123.15×
      wcs
      		 1,069,831 134,338,027 125.57×
      CryptographySingleMultiScaling
      crypt
      		 5,440 794,783 146.09×
      CompressionSingleMultiScaling
      jpeg
      		 1,281 158,034 123.35×
      zlib
      		 64.67 11,514 178.04×
      HypervisorSingleMultiScaling
      clock
      		 40,620 205,605 5.06×
      clone
      		 313.73 16,062 51.20×
      context
      		 9,219 1,539,970 167.04×
      cpu-sched
      		 64.67 11,620 179.68×
      eventfd
      		 156,099 10,431,106 66.82×
      fault
      		 45,959 166,303 3.62×
      fork
      		 5,416 64,503 11.91×
      getrandom
      		 100,495 15,035,724 149.62×
      hrtimers
      		 547,130 4,151,482 7.59×
      mprotect
      		 451,552 37,142,784 82.26×
      mtx
      		 42,375,344 11,206,634,506 264.46×
      munmap
      		 4,462 64,972 14.56×
      null
      		 1,550,979 240,333,784 154.96×
      pipe
      		 3,097,499 106,280,971 34.31×
      priv-instr
      		 1,604,388 21,864,813 13.63×
      resched
      		 5,657,763 59,551,099 10.53×
      switch
      		 373,673 101,294,494 271.08×
      timermix
      		 540,801 81,673,689 151.02×
      tlb-shootdown
      		 12,850 568,878 44.27×
      tsc
      		 888,507 167,126,992 188.10×
      usersyscall
      		 1,162,702 21,411,793 18.42×
      vdso
      		 108,349,005 18,073,502,508 166.81×
      vfork
      		 35,292 129,193 3.66×
      x86syscall
      		 19,965,777 3,111,505,355 155.84×
      yield
      		 386,844,450 358,207,633 0.93×
      zero
      		 10,719,200 1,594,463,516 148.75×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 17,599 2,692,973 153.02×
      expmath
      		 4,020 636,217 158.27×
      fma
      		 1,567,713 231,014,122 147.36×
      fp
      		 202.74 33,451 165.00×
      fractal
      		 9 1,399 155.50×
      hyperbolic
      		 5,473 891,525 162.91×
      logmath
      		 5,725 916,816 160.14×
      matrix
      		 9,320 1,186,788 127.34×
      matrix-3d
      		 1,548 35,154 22.70×
      monte-carlo
      		 463.94 69,255 149.28×
      mpfr
      		 2,409 337,712 140.20×
      powmath
      		 1,842 307,139 166.74×
      trig
      		 2,450 377,879 154.21×
      veccmp
      		 30,295 4,356,227 143.79×
      vecfp
      		 2,396 373,132 155.70×
      vecmath
      		 4,752 769,441 161.91×
      vecshuf
      		 1,009 150,119 148.84×
      vecwide
      		 40,392 5,501,348 136.20×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 12.8 1,869 145.98×
      bsearch
      		 367.65 52,691 143.32×
      bubblesort
      		 1.2 153.8 128.17×
      fibsearch
      		 432.38 66,312 153.37×
      heapsort
      		 14.4 1,981 137.58×
      hsearch
      		 13,667 1,787,393 130.78×
      insertionsort
      		 9.6 1,415 147.44×
      malloc
      		 5,396,383 253,858,606 47.04×
      mcontend
      		 69.1 28,045 405.85×
      mergesort
      		 39.8 5,518 138.64×
      qsort
      		 26.8 3,791 141.44×
      skiplist
      		 8,485 1,261,644 148.69×
      tree
      		 2.6 269.95 103.83×
      MemorySingleMultiScaling
      cache
      		 1,110,292 3,313,130 2.98×
      cachehammer
      		 275,254 12,182,788 44.26×
      cacheline
      		 46.37 4,231 91.25×
      l1cache
      		 1,372 153,790 112.06×
      memcpy
      		 809.78 123,550 152.57×
      memrate
      		 0.97 61.44 63.34×
      memthrash
      		 508.56 2,075 4.08×
      ptr-chase
      		 76,523,461 1,753,432,023 22.91×
      spinmem
      		 294.19 13,688 46.53×
      stream
      		 77.61 310,009 3994.45×
      vm
      		 241,618 312,938 1.30×

      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.12xlarge 4896 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      c8a.48xlarge FAQs