i8g.24xlarge by Amazon Web Services

i8g.24xlarge is a Storage optimized [AWS Graviton processors] Gen8 24xlarge server offered by Amazon Web Services with 96 vCPUs, 768 GiB of memory and 22.5 TB of storage. The pricing starts at 0.8611 USD per hour.
96 vCPU
768 GiB Memory
22.5 TB Storage
Spare SCore
163,579
(All-cores)
1,706
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
i8g.24xlarge
Description
Storage optimized [AWS Graviton processors] Gen8 24xlarge
Family
i8g
Hw Virt
Status
active
Observed At
2026-10-28T19:56:30.293669

Availability

REGION / IDSPOTONDEMAND
Ohio (US) / us-east-2
1.632933 USD/h 8.2368 USD/h
Northern Virgina (US) / us-east-1
2.6001 USD/h 8.2368 USD/h
Oregon (US) / us-west-2
2.8802 USD/h 8.2368 USD/h
Stockholm (SE) / eu-north-1
0.8611 USD/h 8.6112 USD/h
Aragón (ES) / eu-south-2
4.3046 USD/h 9.0768 USD/h
Quebec (CA) / ca-central-1
1.720967 USD/h 9.0768 USD/h
Dublin (IE) / eu-west-1
3.590767 USD/h 9.0768 USD/h
Mumbai (IN) / ap-south-1
3.323667 USD/h 9.3456 USD/h
London (GB) / eu-west-2
2.863633 USD/h 9.5568 USD/h
Paris (FR) / eu-west-3
2.8432 USD/h 9.5568 USD/h
Seoul (KR) / ap-northeast-2
1.333267 USD/h 9.6624 USD/h
Osaka (JP) / ap-northeast-3
2.103233 USD/h 9.6624 USD/h
Tokyo (JP) / ap-northeast-1
1.966633 USD/h 9.6768 USD/h
Frankfurt (DE) / eu-central-1
2.431333 USD/h 9.8208 USD/h
Jakarta (ID) / ap-southeast-3
1.1755 USD/h 9.8736 USD/h
Sydney (AU) / ap-southeast-2
1.7198 USD/h 9.8736 USD/h
Singapore (SG) / ap-southeast-1
3.427667 USD/h 9.8736 USD/h
Sao Paulo (BR) / sa-east-1
2.500933 USD/h 13.152 USD/h

Processor

vCPUs
96
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
96
CPU Speed
2.8 GHz
CPU Architecture
arm64
CPU Manufacturer
AWS
CPU Model
Neoverse-V2
CPU L1D Cache
64 KiB
CPU L1D Cache Total
6 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
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
95.9
Scalability
99.9

System Resources and Accelerators

MEMORY
Memory Amount
768 GiB
Memory Amount Actual
756 GiB
ACCELERATORS
Accelerator Count
0
Accelerator Memory Min
0 MiB
Accelerator Memory Total
0 MiB
Accelerators
    STORAGE
    Storage Size
    22500 GB
    Storage Type
    nvme ssd
    Storages
    • 3750 GB nvme ssd
    • 3750 GB nvme ssd
    • 3750 GB nvme ssd
    • 3750 GB nvme ssd
    • 3750 GB nvme ssd
    • 3750 GB nvme ssd
    NETWORK
    Network Speed Baseline
    56.25 Gbps
    Network Speed Max
    56.25 Gbps
    Network Storage Speed Baseline
    30 Gbps
    Network Storage Speed Max
    30 Gbps
    Inbound Traffic
    0 GB/month
    Outbound Traffic
    0 GB/month
    IPv4
    0

    Server Description

    A high-capacity storage-optimized instance featuring ninety-six arm64 cores, massive local NVMe SSD capacity, and top-tier multi-core performance.

    Storage & DatabaseMemory Optimized

    Amazon Web Services i8g.24xlarge is a storage-optimized server powered by 96 dedicated AWS Graviton Neoverse-V2 arm64 cores running at 2.8 GHz. It features 768 GB of RAM and a substantial 22,500 GB of local NVMe SSD storage, managed by the AWS Nitro hypervisor. Operating with a baseline network bandwidth of 56 Gbps, this instance delivers top-tier multi-core CPU performance, exceptional memory bandwidth, and high database operation throughput. While single-core performance sits in the average tier, its massive local storage and parallel processing capabilities make it highly efficient for data-intensive workloads. It is designed for large-scale databases, high-throughput web serving, and memory-intensive caching systems.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    6.5Score
    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) 23,374,440 ops/sec 1,919,289 ops/sec 12 50.00% 50.00% +250.00%
    Redis RPS (pipeline=16, SET) 124,371,187 ops/sec 11,728,058 ops/sec 10 20.00% 20.00% +58.00%
    PassMark Memory Mark (composite) 3,347 2,416 1.4 10.00% 10.00% +3.40%
    Memory bandwidth (read, 16 MB ~ L3) 545,581 MB/sec 108,466 MB/sec 5 10.00% 10.00% +17.00%
    PassMark single-thread CPU 1,944 Mops/s 2,365 Mops/s 0.79 10.00% 10.00% -2.30%

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 1,894

    Geekbench Multi-Core

    Score: 26,076

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 56,754
    Compression
    		 638,021
    Encryption
    		 18,119
    Extended Instructions
    		 80,465
    Floating Point Maths
    		 581,269
    Integer Maths
    		 500,408
    Physics
    		 19,002
    Prime Numbers
    		 825
    Single Threaded
    		 1,944
    String Sorting
    		 432,672

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 3,347
    Database Operations
    		 47,379
    Memory Latency
    		 48
    Memory Read Cached
    		 20,985
    Memory Read Uncached
    		 20,042
    Memory Write
    		 21,289

    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

    INSTANCEvCPUsMEMORYAccelerators
    i8g.large 216 GiB0
    i8g.xlarge 432 GiB0
    i8g.2xlarge 864 GiB0
    i8g.4xlarge 16128 GiB0
    i8g.8xlarge 32256 GiB0
    i8g.12xlarge 48384 GiB0
    i8g.16xlarge 64512 GiB0

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYAccelerators

    i8g.24xlarge FAQs