c8i.metal-48xl by Amazon Web Services

c8i.metal-48xl is a Compute optimized [Intel processors] Gen8 metal-48xl server offered by Amazon Web Services with 192 vCPUs, 384 GiB of memory and 0 GB of storage. The pricing starts at 0.8996 USD per hour.
192 vCPU
384 GiB Memory
Spare SCore
209,049
(All-cores)
2,144
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
c8i.metal-48xl
Description
Compute optimized [Intel processors] Gen8 metal-48xl
Family
c8i
Hw Virt
Average Time To Start
26
Status
active
Observed At
2026-10-31T04:43:58.140365

Availability

REGION / IDSPOTONDEMAND
(MY) / ap-southeast-5
8.704233 USD/h 8.8166 USD/h
Ohio (US) / us-east-2
1.526233 USD/h 8.9962 USD/h
Oregon (US) / us-west-2
1.99175 USD/h 8.9962 USD/h
Northern Virgina (US) / us-east-1
3.64692 USD/h 8.9962 USD/h
Mumbai (IN) / ap-south-1
5.787667 USD/h 8.9962 USD/h
Hyderabad (IN) / ap-south-2
7.124233 USD/h 8.9962 USD/h
Stockholm (SE) / eu-north-1
1.337267 USD/h 9.6317 USD/h
Aragón (ES) / eu-south-2
4.3688 USD/h 9.6518 USD/h
Dublin (IE) / eu-west-1
3.548 USD/h 9.6528 USD/h
Quebec (CA) / ca-central-1
7.617267 USD/h 9.8429 USD/h
Seoul (KR) / ap-northeast-2
1.79 USD/h 10.1606 USD/h
Frankfurt (DE) / eu-central-1
4.5888 USD/h 10.2662 USD/h
Singapore (SG) / ap-southeast-1
3.3307 USD/h 10.3728 USD/h
Paris (FR) / eu-west-3
7.482733 USD/h 10.6896 USD/h
London (GB) / eu-west-2
7.724033 USD/h 10.6896 USD/h
California (US) / us-west-1
1.1219 USD/h 11.2186 USD/h
Tokyo (JP) / ap-northeast-1
4.8528 USD/h 11.3251 USD/h
Sydney (AU) / ap-southeast-2
11.7485 USD/h 11.7485 USD/h
Cape Town (ZA) / af-south-1
12.0662 USD/h 12.0662 USD/h
(NZ) / ap-southeast-6
12.336 USD/h 12.336 USD/h
Sao Paulo (BR) / sa-east-1
3.6153 USD/h 13.8653 USD/h

Processor

vCPUs
192
CPU Allocation
Dedicated
CPU Cores
96
CPU Speed
3.9 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU Model
6975P-C
CPU L1D Cache
48 KiB
CPU L1D Cache Total
5 MiB
CPU L1I Cache
64 KiB
CPU L1I Cache Total
6 MiB
CPU L2 Cache
2 MiB
CPU L2 Cache Total
192 MiB
CPU L3 Cache
480 MiB
CPU L3 Cache Total
480 MiB
CPU Flags
fpu, vme, de, pse, tsc, msr, pae, mce, cx8, apic, sep, mtrr, pge, mca, cmov, pat, pse36, clflush, dts, acpi, mmx, fxsr, sse, sse2, ss, ht, tm, pbe, syscall, nx, pdpe1gb, rdtscp, lm, constant_tsc, art, arch_perfmon, pebs, bts, rep_good, nopl, xtopology, nonstop_tsc, cpuid, aperfmperf, tsc_known_freq, pni, pclmulqdq, dtes64, monitor, ds_cpl, vmx, smx, est, tm2, ssse3, sdbg, fma, cx16, xtpr, pdcm, pcid, dca, sse4_1, sse4_2, x2apic, movbe, popcnt, tsc_deadline_timer, aes, xsave, avx, f16c, rdrand, lahf_lm, abm, 3dnowprefetch, cpuid_fault, epb, cat_l3, cat_l2, cdp_l3, intel_ppin, cdp_l2, ssbd, mba, ibrs, ibpb, stibp, ibrs_enhanced, tpr_shadow, flexpriority, ept, vpid, ept_ad, fsgsbase, tsc_adjust, bmi1, avx2, smep, bmi2, erms, invpcid, cqm, rdt_a, avx512f, avx512dq, rdseed, adx, smap, avx512ifma, clflushopt, clwb, intel_pt, avx512cd, sha_ni, avx512bw, avx512vl, xsaveopt, xsavec, xgetbv1, xsaves, cqm_llc, cqm_occup_llc, cqm_mbm_total, cqm_mbm_local, split_lock_detect, user_shstk, avx_vnni, avx512_bf16, wbnoinvd, dtherm, ida, arat, pln, pts, hwp, hwp_act_window, hwp_epp, hwp_pkg_req, vnmi, avx512vbmi, umip, pku, ospke, waitpkg, avx512_vbmi2, gfni, vaes, vpclmulqdq, avx512_vnni, avx512_bitalg, tme, avx512_vpopcntdq, la57, rdpid, bus_lock_detect, cldemote, movdiri, movdir64b, enqcmd, fsrm, md_clear, serialize, tsxldtrk, pconfig, arch_lbr, ibt, amx_bf16, avx512_fp16, amx_tile, amx_int8, flush_l1d, arch_capabilities
Ecpus
97.5
Scalability
50.78

System Resources and Accelerators

MEMORY
Memory Amount
384 GiB
Memory Amount Actual
384 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
      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 bare-metal server delivering top-tier multi-core compute performance and advanced matrix acceleration for parallelized enterprise workloads.

      Compute OptimizedGeneral Purpose

      Amazon Web Services c8i.metal-48xl is a bare-metal, compute-optimized server designed for high-throughput parallel workloads. It features 192 vCPUs across 96 physical Intel Xeon 6975P-C cores running at 3.9 GHz, paired with 384.0 GB of RAM. The x86_64 architecture includes Intel Advanced Matrix Extensions (AMX) and AVX-512, which drive top-tier multi-core CPU performance, software compilation, and database operations. While the server lacks local storage and dedicated GPUs, its high-speed 75 Gbps baseline network bandwidth and top-tier memory bandwidth support data-intensive operations. Tradeoffs include a low memory-to-core ratio of 2.0 GB per core and moderate single-core performance. This instance is highly suited for compute-heavy workloads such as high-performance computing, multi-threaded software compilation, and CPU-based language model inference.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      9.6Score
      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) 35,868,170 ops/sec 1,918,343 ops/sec 19 50.00% 50.00% +340.00%
      Redis RPS (pipeline=16, SET) 185,170,699 ops/sec 11,704,734 ops/sec 16 20.00% 20.00% +74.00%
      PassMark Memory Mark (composite) 2,831 2,416 1.2 10.00% 10.00% +1.80%
      Memory bandwidth (read, 16 MB ~ L3) 706,568 MB/sec 108,466 MB/sec 6.5 10.00% 10.00% +21.00%
      PassMark single-thread CPU 3,302 Mops/s 2,365 Mops/s 1.4 10.00% 10.00% +3.40%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 2,191

      Geekbench Multi-Core

      Score: 23,340

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 146,398
      Compression
      		 3,620,145
      Encryption
      		 217,929
      Extended Instructions
      		 245,594
      Floating Point Maths
      		 722,938
      Integer Maths
      		 997,349
      Physics
      		 28,798
      Prime Numbers
      		 1,676
      Single Threaded
      		 3,302
      String Sorting
      		 468,220

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2,831
      Database Operations
      		 37,489
      Memory Latency
      		 65
      Memory Read Cached
      		 28,431
      Memory Read Uncached
      		 16,703
      Memory Write
      		 11,771

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 151.38 83.16 0.55×
      bitops
      		 165,907 18,305,650 110.34×
      branch
      		 154,816 24,197,689 156.30×
      funccall
      		 860.72 104,818 121.78×
      funcret
      		 14,126 2,103,445 148.91×
      hash
      		 191,352 26,932,895 140.75×
      intmath
      		 73,377 8,448,447 115.14×
      nop
      		 289,785 30,151,749 104.05×
      prime
      		 530,741 62,722,509 118.18×
      rotate
      		 109,546 18,695,292 170.66×
      str
      		 1,079,472 132,633,611 122.87×
      wcs
      		 792,279 80,622,969 101.76×
      CryptographySingleMultiScaling
      crypt
      		 3,743 435,183 116.26×
      CompressionSingleMultiScaling
      jpeg
      		 934.67 105,919 113.32×
      zlib
      		 56.48 10,264 181.73×
      HypervisorSingleMultiScaling
      clock
      		 32,276 299,857 9.29×
      clone
      		 478.36 34,099 71.28×
      context
      		 6,063 970,478 160.07×
      cpu-sched
      		 62.85 11,238 178.81×
      eventfd
      		 168,445 2,227,682 13.22×
      fault
      		 35,786 239,998 6.71×
      fork
      		 2,640 91,052 34.49×
      getrandom
      		 64,538 8,916,853 138.16×
      hrtimers
      		 146,532 10,516,685 71.77×
      mprotect
      		 759,758 14,439,125 19.00×
      mtx
      		 25,402,512 6,477,146,955 254.98×
      munmap
      		 2,020 88,749 43.93×
      null
      		 1,131,950 167,371,327 147.86×
      pipe
      		 783,592 136,118,484 173.71×
      priv-instr
      		 937,767 9,093,803 9.70×
      resched
      		 12,087,097 31,331,972 2.59×
      switch
      		 306,648 40,795,433 133.04×
      timermix
      		 863,340 107,460,140 124.47×
      tlb-shootdown
      		 7,285 202,874 27.85×
      tsc
      		 1,084,060 185,715,858 171.32×
      usersyscall
      		 797,139 8,971,663 11.25×
      vdso
      		 140,424,159 19,531,232,827 139.09×
      vfork
      		 4,818 178,137 36.97×
      x86syscall
      		 12,645,349 2,043,751,312 161.62×
      yield
      		 294,509,790 315,802,903 1.07×
      zero
      		 7,597,805 1,179,634,730 155.26×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 18,259 2,219,837 121.57×
      expmath
      		 3,892 544,396 139.89×
      fma
      		 1,325,483 172,591,584 130.21×
      fp
      		 223.2 32,228 144.39×
      fractal
      		 7.8 1,017 130.41×
      hyperbolic
      		 4,513 627,400 139.03×
      logmath
      		 5,731 879,851 153.53×
      matrix
      		 5,726 678,076 118.41×
      matrix-3d
      		 629.75 25,615 40.68×
      monte-carlo
      		 344.31 52,115 151.36×
      mpfr
      		 1,933 216,574 112.04×
      powmath
      		 2,176 321,087 147.54×
      trig
      		 3,039 366,061 120.44×
      veccmp
      		 27,258 2,871,924 105.36×
      vecfp
      		 1,681 206,020 122.58×
      vecmath
      		 4,317 571,218 132.32×
      vecshuf
      		 896.57 97,850 109.14×
      vecwide
      		 37,430 3,755,764 100.34×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 10.6 1,267 119.56×
      bsearch
      		 344.79 39,595 114.84×
      bubblesort
      		 1.2 115.2 96.00×
      fibsearch
      		 337.65 41,364 122.50×
      heapsort
      		 11 1,417 128.79×
      hsearch
      		 9,651 1,030,120 106.73×
      insertionsort
      		 14.2 1,344 94.68×
      malloc
      		 3,298,562 117,220,029 35.54×
      mcontend
      		 84.27 33,198 393.95×
      mergesort
      		 34 4,496 132.24×
      qsort
      		 24.2 3,085 127.49×
      skiplist
      		 7,048 1,037,179 147.16×
      tree
      		 1.8 153.33 85.18×
      MemorySingleMultiScaling
      cache
      		 320,900 9,260,412 28.86×
      cachehammer
      		 169,264 7,578,096 44.77×
      cacheline
      		 57.56 2,434 42.28×
      l1cache
      		 818.39 27,228 33.27×
      memcpy
      		 769.23 74,747 97.17×
      memrate
      		 0.13 20.34 156.46×
      memthrash
      		 392.98 1,876 4.77×
      ptr-chase
      		 28,863,049 1,315,922,930 45.59×
      spinmem
      		 334.99 12,018 35.88×
      stream
      		 1.43 5,853 4093.10×
      vm
      		 159,173 311,542 1.96×

      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
      c8i.large 24 GiB0
      c8i.xlarge 48 GiB0
      c8i.2xlarge 816 GiB0
      c8i.4xlarge 1632 GiB0
      c8i.8xlarge 3264 GiB0
      c8i.12xlarge 4896 GiB0
      c8i.16xlarge 64128 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      c8i.metal-48xl FAQs