c8i.metal-96xl by Amazon Web Services

c8i.metal-96xl is a Compute optimized [Intel processors] Gen8 metal-96xl server offered by Amazon Web Services with 384 vCPUs, 768 GiB of memory and 0 GB of storage. The pricing starts at 1.7633 USD per hour.
384 vCPU
768 GiB Memory
Spare SCore
417,806
(All-cores)
2,141
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
c8i.metal-96xl
Description
Compute optimized [Intel processors] Gen8 metal-96xl
Family
c8i
Hw Virt
Average Time To Start
32.33
Status
active
Observed At
2026-10-30T22:24:57.708353

Availability

REGION / IDSPOTONDEMAND
(MY) / ap-southeast-5
1.7633 USD/h 17.6333 USD/h
Mumbai (IN) / ap-south-1
7.1969 USD/h 17.9923 USD/h
Hyderabad (IN) / ap-south-2
1.7992 USD/h 17.9923 USD/h
Ohio (US) / us-east-2
6.5278 USD/h 17.9923 USD/h
Northern Virgina (US) / us-east-1
6.64712 USD/h 17.9923 USD/h
Oregon (US) / us-west-2
7.18205 USD/h 17.9923 USD/h
Stockholm (SE) / eu-north-1
2.446367 USD/h 19.2634 USD/h
Aragón (ES) / eu-south-2
7.436633 USD/h 19.3037 USD/h
Dublin (IE) / eu-west-1
5.4781 USD/h 19.3056 USD/h
Quebec (CA) / ca-central-1
2.732367 USD/h 19.6858 USD/h
Seoul (KR) / ap-northeast-2
2.0321 USD/h 20.3213 USD/h
Frankfurt (DE) / eu-central-1
3.9547 USD/h 20.5325 USD/h
Singapore (SG) / ap-southeast-1
12.580733 USD/h 20.7456 USD/h
London (GB) / eu-west-2
8.581833 USD/h 21.3792 USD/h
Paris (FR) / eu-west-3
15.490767 USD/h 21.3792 USD/h
California (US) / us-west-1
2.26415 USD/h 22.4371 USD/h
Tokyo (JP) / ap-northeast-1
7.957333 USD/h 22.6502 USD/h
Sydney (AU) / ap-southeast-2
18.843633 USD/h 23.497 USD/h
Cape Town (ZA) / af-south-1
2.4132 USD/h 24.1325 USD/h
(NZ) / ap-southeast-6
2.4672 USD/h 24.672 USD/h
Sao Paulo (BR) / sa-east-1
2.7731 USD/h 27.7306 USD/h

Processor

vCPUs
384
CPU Allocation
Dedicated
CPU Cores
192
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
9 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
480 MiB
CPU L3 Cache Total
960 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
195.2
Scalability
50.83

System Resources and Accelerators

MEMORY
Memory Amount
768 GiB
Memory Amount Actual
768 GiB
Memory Generation
DDR5
Memory Speed
7200 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
      100 Gbps
      Network Speed Max
      100 Gbps
      Network Storage Speed Baseline
      80 Gbps
      Network Storage Speed Max
      80 Gbps
      Inbound Traffic
      0 GB/month
      Outbound Traffic
      0 GB/month
      IPv4
      0

      CPU and System Topology

      Server Description

      A bare-metal compute platform featuring three hundred eighty-four Intel vCPUs and DDR5 memory for high-throughput parallel processing workloads.

      Compute OptimizedGeneral Purpose

      Amazon Web Services c8i.metal-96xl is a bare-metal, compute-optimized server featuring 384 vCPUs across 192 physical Intel Xeon 6975P-C cores running at 3.9 GHz. It includes 768.0 GB of DDR5 memory at 7 GHz, offering a 2.0 GB per core ratio, but contains no local storage or GPUs. Network connectivity is supported by a 100 Gbps baseline bandwidth. Benchmark results place this server in the top tier for multi-core CPU performance, memory bandwidth, and database operations, aided by Intel AMX and AVX-512 instruction sets. However, text generation speeds for large language models remain average to poor due to the lack of hardware accelerators. This bare-metal instance is designed for compute-heavy workloads, multi-threaded software compilation, and high-throughput database tasks where direct hardware access is required.

      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) 58,602,527 ops/sec 1,918,343 ops/sec 31 50.00% 50.00% +460.00%
      Redis RPS (pipeline=16, SET) 342,965,920 ops/sec 11,704,734 ops/sec 28 20.00% 20.00% +95.00%
      PassMark Memory Mark (composite) 2,722 2,416 1.1 10.00% 10.00% +0.96%
      Memory bandwidth (read, 16 MB ~ L3) 1,389,413 MB/sec 108,466 MB/sec 13 10.00% 10.00% +29.00%
      PassMark single-thread CPU 3,305 Mops/s 2,365 Mops/s 1.4 10.00% 10.00% +3.40%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 2,223

      Geekbench Multi-Core

      Score: 18,050

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 181,126
      Compression
      		 7,062,740
      Encryption
      		 422,513
      Extended Instructions
      		 476,593
      Floating Point Maths
      		 1,440,127
      Integer Maths
      		 1,989,670
      Physics
      		 54,013
      Prime Numbers
      		 3,331
      Single Threaded
      		 3,305
      String Sorting
      		 892,504

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2,722
      Database Operations
      		 38,197
      Memory Latency
      		 65
      Memory Read Cached
      		 27,846
      Memory Read Uncached
      		 16,571
      Memory Write
      		 8,784

      Stress-ng Stressors

      CPU integerSingleMultiScaling
      atomic
      		 171.71 87.78 0.51×
      bitops
      		 165,847 36,401,152 219.49×
      branch
      		 154,707 48,080,697 310.79×
      funccall
      		 860.75 206,123 239.47×
      funcret
      		 14,021 4,147,454 295.81×
      hash
      		 191,109 53,373,716 279.28×
      intmath
      		 73,314 16,736,876 228.29×
      nop
      		 289,622 60,294,333 208.18×
      prime
      		 530,461 120,644,380 227.43×
      rotate
      		 109,454 35,302,885 322.54×
      str
      		 1,078,374 224,109,177 207.82×
      wcs
      		 778,224 153,267,322 196.95×
      CryptographySingleMultiScaling
      crypt
      		 3,741 858,897 229.60×
      CompressionSingleMultiScaling
      jpeg
      		 914.31 192,685 210.74×
      zlib
      		 56.74 20,271 357.26×
      HypervisorSingleMultiScaling
      clock
      		 20,496 163,954 8.00×
      clone
      		 476.57 30,539 64.08×
      context
      		 6,058 1,936,711 319.71×
      cpu-sched
      		 66.49 14,980 225.30×
      eventfd
      		 157,802 753,526 4.78×
      fault
      		 35,571 123,493 3.47×
      fork
      		 2,296 52,373 22.81×
      getrandom
      		 64,477 17,461,885 270.82×
      hrtimers
      		 1,388,240 7,505,752 5.41×
      mprotect
      		 593,260 9,503,351 16.02×
      mtx
      		 19,393,461 11,807,110,572 608.82×
      munmap
      		 1,912 52,518 27.47×
      null
      		 1,130,198 319,028,987 282.28×
      pipe
      		 640,640 209,041,673 326.30×
      priv-instr
      		 939,374 5,957,717 6.34×
      resched
      		 11,396,965 86,202,807 7.56×
      switch
      		 291,857 65,486,164 224.38×
      timermix
      		 863,196 197,746,236 229.09×
      tlb-shootdown
      		 5,633 237,076 42.08×
      tsc
      		 1,083,149 372,044,918 343.48×
      usersyscall
      		 797,963 5,790,953 7.26×
      vdso
      		 140,310,252 38,740,142,011 276.10×
      vfork
      		 4,079 102,358 25.10×
      x86syscall
      		 12,623,335 3,895,009,677 308.56×
      yield
      		 692,369,489 638,602,344 0.92×
      zero
      		 7,590,935 2,347,040,001 309.19×
      CPU float/SIMDSingleMultiScaling
      eigen
      		 18,227 4,406,077 241.73×
      expmath
      		 3,890 1,061,963 272.98×
      fma
      		 1,324,797 338,683,396 255.65×
      fp
      		 208.33 63,170 303.22×
      fractal
      		 7.8 1,947 249.58×
      hyperbolic
      		 4,511 1,229,027 272.43×
      logmath
      		 5,727 1,719,596 300.26×
      matrix
      		 6,178 1,250,510 202.41×
      matrix-3d
      		 564.13 50,137 88.87×
      monte-carlo
      		 344.36 101,379 294.40×
      mpfr
      		 1,923 418,634 217.65×
      powmath
      		 2,175 622,635 286.27×
      trig
      		 3,038 703,659 231.59×
      veccmp
      		 27,180 5,572,999 205.04×
      vecfp
      		 1,679 413,922 246.58×
      vecmath
      		 4,315 1,130,795 262.09×
      vecshuf
      		 896.19 192,869 215.21×
      vecwide
      		 37,399 7,259,276 194.10×
      AlgorithmsSingleMultiScaling
      bitonicsort
      		 10.6 2,532 238.89×
      bsearch
      		 344.48 77,141 223.94×
      bubblesort
      		 1.2 230.6 192.17×
      fibsearch
      		 336.77 82,917 246.21×
      heapsort
      		 11 2,771 251.90×
      hsearch
      		 9,689 2,007,202 207.16×
      insertionsort
      		 14.2 2,688 189.32×
      malloc
      		 2,312,684 131,612,086 56.91×
      mcontend
      		 33.33 48,241 1447.37×
      mergesort
      		 34 8,694 255.70×
      qsort
      		 24.2 6,007 248.24×
      skiplist
      		 7,042 2,040,715 289.80×
      tree
      		 1.8 306.95 170.53×
      MemorySingleMultiScaling
      cache
      		 258,414 185,723 0.72×
      cachehammer
      		 127,635 - -
      cacheline
      		 13.39 24.52 1.83×
      l1cache
      		 816.3 1,537 1.88×
      memcpy
      		 769.09 148,408 192.97×
      memrate
      		 0.13 35.86 275.85×
      memthrash
      		 328.99 2,183 6.64×
      ptr-chase
      		 29,583,968 2,626,261,318 88.77×
      spinmem
      		 275.59 24,006 87.11×
      stream
      		 0.42 24.14 57.48×
      vm
      		 146,525 - -

      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-96xl FAQs