logo

i8ge.18xlarge by Amazon Web Services

i8ge.18xlarge is a Storage optimized [AWS Graviton processors] [Extra storage or memory] Gen8 18xlarge server offered by Amazon Web Services with 72 vCPUs, 576 GiB of memory and 45 TB of storage. The pricing starts at 0.8543 USD per hour.
72 vCPU
576 GiB Memory
45 TB Storage
Spare SCore
122783
(All-cores)
1706
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
i8ge.18xlarge
Description
Storage optimized [AWS Graviton processors] [Extra storage or memory] Gen8 18xlarge
Family
i8ge
Hw Virt
Status
active
Observed At
2026-07-26T14:12:59.549539

Availability

REGION / IDSPOTONDEMAND
Ohio (US) / us-east-2
0.910467 USD/h 8.5428 USD/h
Oregon (US) / us-west-2
2.2158 USD/h 8.5428 USD/h
Northern Virgina (US) / us-east-1
4.082267 USD/h 8.5428 USD/h
Stockholm (SE) / eu-north-1
1.312267 USD/h 8.9586 USD/h
(TH) / ap-southeast-7
3.002233 USD/h 9.2232 USD/h
(MY) / ap-southeast-5
3.365933 USD/h 9.2232 USD/h
Dublin (IE) / eu-west-1
3.009233 USD/h 9.45 USD/h
Quebec (CA) / ca-central-1
3.6163 USD/h 9.45 USD/h
Mumbai (IN) / ap-south-1
1.070433 USD/h 9.7146 USD/h
Paris (FR) / eu-west-3
1.880967 USD/h 9.9414 USD/h
London (GB) / eu-west-2
3.6537 USD/h 9.9414 USD/h
Seoul (KR) / ap-northeast-2
1.525233 USD/h 10.0548 USD/h
Tokyo (JP) / ap-northeast-1
1.7703 USD/h 10.0548 USD/h
Frankfurt (DE) / eu-central-1
2.091433 USD/h 10.206 USD/h
Sydney (AU) / ap-southeast-2
1.759267 USD/h 10.2438 USD/h
Singapore (SG) / ap-southeast-1
5.1017 USD/h 10.2438 USD/h
Hong Kong (HK) / ap-east-1
2.3013 USD/h 11.2833 USD/h

Processor

vCPUs
72
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
72
CPU Speed
2.8 GHz
CPU Architecture
arm64
CPU Manufacturer
AWS
CPU Family
ARMv9
CPU Model
Neoverse-V2
CPU L1D Cache
64 KiB
CPU L1D Cache Total
5 MiB
CPU L1I Cache
64 KiB
CPU L1I Cache Total
5 MiB
CPU L2 Cache
2 MiB
CPU L2 Cache Total
144 MiB
CPU L3 Cache
36 MiB
CPU L3 Cache Total
36 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
Ecpus
72
Scalability
100

System Resources and Accelerators

MEMORY
Memory Amount
576 GiB
Memory Amount Actual
567 GiB
GPU
GPU Count
0
GPU Memory Min
0 MiB
GPU Memory Total
0 MiB
GPUs
    STORAGE
    Storage Size
    45000 GB
    Storage Type
    nvme ssd
    Storages
    • 7500 GB nvme ssd
    • 7500 GB nvme ssd
    • 7500 GB nvme ssd
    • 7500 GB nvme ssd
    • 7500 GB nvme ssd
    • 7500 GB nvme ssd
    NETWORK
    Network Speed Baseline
    112.5 Gbps
    Network Speed Max
    112.5 Gbps
    Network Storage Speed Baseline
    22.5 Gbps
    Network Storage Speed Max
    22.5 Gbps
    Inbound Traffic
    0 GB/month
    Outbound Traffic
    0 GB/month
    IPv4
    0

    Server Description

    An ARM-based storage-optimized server featuring massive local NVMe capacity and top-tier memory bandwidth for data-intensive database workloads.

    Storage & DatabaseMemory Optimized

    Amazon Web Services i8ge.18xlarge is a storage-optimized server powered by 72 dedicated physical cores of the ARMv9 AWS Graviton Neoverse-V2 processor running at 2.8 GHz. Operating on the Nitro hypervisor, it features 576.0 GB of memory and a massive 45,000 GB of local NVMe SSD storage, supported by a 112 Gbps baseline network bandwidth. Benchmark data highlights top-tier performance in memory bandwidth, Redis SET operations, and Passmark database operations, alongside strong multi-core CPU performance. While single-core performance is average, the server's high resource density makes it a highly efficient choice for data-intensive workloads. It is best suited for large-scale databases, high-throughput static web serving, memory-intensive caching layers, and software compilation pipelines.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    4.77Score
    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) 14,115,663 ops/sec 1,896,415 ops/sec 7.44 50.00% 50.00% +173.00%
    Redis RPS (pipeline=16, SET) 78,595,762 ops/sec 11,539,523 ops/sec 6.81 20.00% 20.00% +46.80%
    PassMark Memory Mark (composite) 3,372 2,411 1.4 10.00% 10.00% +3.42%
    Memory bandwidth (read, 16 MB ~ L3) 540,010 MB/sec 107,368 MB/sec 5.03 10.00% 10.00% +17.50%
    PassMark single-thread CPU 1,943 Mops/s 2,363 Mops/s 0.822 10.00% 10.00% -1.94%

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 1,894

    Geekbench Multi-Core

    Score: 25,790

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 47698
    Compression
    		 478218
    Encryption
    		 13640
    Extended Instructions
    		 62268
    Floating Point Maths
    		 435987
    Integer Maths
    		 375121
    Physics
    		 17470
    Prime Numbers
    		 734
    Single Threaded
    		 1943
    String Sorting
    		 328777

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 3372
    Database Operations
    		 47572
    Memory Latency
    		 47
    Memory Read Cached
    		 20972
    Memory Read Uncached
    		 20164
    Memory Write
    		 21287

    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

    Alternatives

    Servers of the Same Family

    INSTANCEvCPUsMEMORYGPUs
    i8ge.large 216 GiB0
    i8ge.xlarge 432 GiB0
    i8ge.2xlarge 864 GiB0
    i8ge.3xlarge 1296 GiB0
    i8ge.6xlarge 24192 GiB0
    i8ge.12xlarge 48384 GiB0
    i8ge.24xlarge 96768 GiB0

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYGPUs

    i8ge.18xlarge FAQs