i8g.4xlarge by Amazon Web Services

i8g.4xlarge is a Storage optimized [AWS Graviton processors] Gen8 4xlarge server offered by Amazon Web Services with 16 vCPUs, 128 GiB of memory and 3.75 TB of storage. The pricing starts at 0.1435 USD per hour.
16 vCPU
128 GiB Memory
3.75 TB Storage
Spare SCore
27,304
(All-cores)
1,707
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
i8g.4xlarge
Description
Storage optimized [AWS Graviton processors] Gen8 4xlarge
Family
i8g
Hw Virt
Status
active
Observed At
2026-09-14T01:58:16.701267

Availability

REGION / IDSPOTONDEMAND
Ohio (US) / us-east-2
0.2854 USD/h 1.3728 USD/h
Oregon (US) / us-west-2
0.377525 USD/h 1.3728 USD/h
Northern Virgina (US) / us-east-1
0.90055 USD/h 1.3728 USD/h
Stockholm (SE) / eu-north-1
0.175767 USD/h 1.4352 USD/h
Aragón (ES) / eu-south-2
0.189933 USD/h 1.5128 USD/h
Quebec (CA) / ca-central-1
0.386067 USD/h 1.5128 USD/h
Dublin (IE) / eu-west-1
0.594233 USD/h 1.5128 USD/h
Mumbai (IN) / ap-south-1
0.4456 USD/h 1.5576 USD/h
London (GB) / eu-west-2
0.453433 USD/h 1.5928 USD/h
Paris (FR) / eu-west-3
- 1.5928 USD/h
Seoul (KR) / ap-northeast-2
0.442233 USD/h 1.6104 USD/h
Osaka (JP) / ap-northeast-3
0.5019 USD/h 1.6104 USD/h
Tokyo (JP) / ap-northeast-1
0.483833 USD/h 1.6128 USD/h
Frankfurt (DE) / eu-central-1
0.601967 USD/h 1.6368 USD/h
Sydney (AU) / ap-southeast-2
0.468067 USD/h 1.6456 USD/h
Singapore (SG) / ap-southeast-1
0.502233 USD/h 1.6456 USD/h
Jakarta (ID) / ap-southeast-3
- 1.6456 USD/h
Sao Paulo (BR) / sa-east-1
0.3491 USD/h 2.192 USD/h

Processor

vCPUs
16
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
16
CPU Speed
2.8 GHz
CPU Architecture
arm64
CPU Manufacturer
AWS
CPU Model
Neoverse-V2
CPU L1D Cache
64 KiB
CPU L1D Cache Total
1 MiB
CPU L1I Cache
64 KiB
CPU L1I Cache Total
1 MiB
CPU L2 Cache
2 MiB
CPU L2 Cache Total
32 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, ssbs, sb, paca, pacg, dcpodp, sve2, sveaes, svepmull, svebitperm, svesha3, flagm2, frint, svei8mm, svebf16, i8mm, bf16, dgh, rng, bti
Ecpus
16
Scalability
100

System Resources and Accelerators

MEMORY
Memory Amount
128 GiB
Memory Amount Actual
126 GiB
GPU
GPU Count
0
GPU Memory Min
0 MiB
GPU Memory Total
0 MiB
GPUs
    STORAGE
    Storage Size
    3750 GB
    Storage Type
    nvme ssd
    Storages
    • 3750 GB nvme ssd
    NETWORK
    Network Speed Baseline
    9.375 Gbps
    Network Speed Max
    25 Gbps
    Network Storage Speed Baseline
    5 Gbps
    Network Storage Speed Max
    10 Gbps
    Inbound Traffic
    0 GB/month
    Outbound Traffic
    0 GB/month
    IPv4
    0

    Server Description

    An arm64 storage-optimized platform combining dedicated Graviton cores, high-capacity local NVMe SSDs, and top-tier memory bandwidth for database workloads.

    Storage & DatabaseMemory OptimizedGeneral Purpose

    Amazon Web Services i8g.4xlarge is an arm64 storage-optimized instance powered by a 16-core AWS Graviton Neoverse-V2 processor running at 2.8 GHz. It features 128.0 GB of RAM, 3750 GB of bundled local NVMe SSD storage, and a baseline network bandwidth of 9 Gbps. Operating on the Nitro hypervisor, the instance delivers strong memory performance, with uncached large-block memory read bandwidth of 296.95 GB/sec and a top-tier Passmark memory score. Database operations and multi-threaded decompression benchmarks also rank in the top 25%. While CPU-based machine learning inference is a performance bottleneck, the server's high-capacity local storage and strong memory throughput offer excellent qualitative cost efficiency for data-intensive applications. It is highly suited for database hosting, caching layers, and high-throughput storage workloads.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    1.76Score
    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) 3,513,047 ops/sec 1,917,397 ops/sec 1.83 50.00% 50.00% +35.30%
    Redis RPS (pipeline=16, SET) 23,167,422 ops/sec 11,681,410 ops/sec 1.98 20.00% 20.00% +14.60%
    PassMark Memory Mark (composite) 3,336 2,418 1.38 10.00% 10.00% +3.27%
    Memory bandwidth (read, 16 MB ~ L3) 333,913 MB/sec 108,140 MB/sec 3.09 10.00% 10.00% +11.90%
    PassMark single-thread CPU 1,945 Mops/s 2,365 Mops/s 0.822 10.00% 10.00% -1.94%

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 1,887

    Geekbench Multi-Core

    Score: 15,908

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 14565
    Compression
    		 106496
    Encryption
    		 3012
    Extended Instructions
    		 14532
    Floating Point Maths
    		 97041
    Integer Maths
    		 83508
    Physics
    		 4901
    Prime Numbers
    		 265
    Single Threaded
    		 1945
    String Sorting
    		 74206

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 3336
    Database Operations
    		 24106
    Memory Latency
    		 47
    Memory Read Cached
    		 21209
    Memory Read Uncached
    		 20191
    Memory Write
    		 21300

    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
    i8g.large 216 GiB0
    i8g.xlarge 432 GiB0
    i8g.2xlarge 864 GiB0
    i8g.8xlarge 32256 GiB0
    i8g.12xlarge 48384 GiB0
    i8g.16xlarge 64512 GiB0
    i8g.24xlarge 96768 GiB0

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYGPUs

    i8g.4xlarge FAQs