i8g.16xlarge by Amazon Web Services

i8g.16xlarge is a Storage optimized [AWS Graviton processors] Gen8 16xlarge server offered by Amazon Web Services with 64 vCPUs, 512 GiB of memory and 15 TB of storage. The pricing starts at 0.5741 USD per hour.
64 vCPU
512 GiB Memory
15 TB Storage
Spare SCore
109,147
(All-cores)
1,707
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
i8g.16xlarge
Description
Storage optimized [AWS Graviton processors] Gen8 16xlarge
Family
i8g
Hw Virt
Status
active
Observed At
2026-09-05T18:49:41.990932

Availability

REGION / IDSPOTONDEMAND
Ohio (US) / us-east-2
0.909133 USD/h 5.4912 USD/h
Oregon (US) / us-west-2
1.579675 USD/h 5.4912 USD/h
Northern Virgina (US) / us-east-1
1.928175 USD/h 5.4912 USD/h
Stockholm (SE) / eu-north-1
0.5741 USD/h 5.7408 USD/h
Aragón (ES) / eu-south-2
2.399233 USD/h 6.0512 USD/h
Quebec (CA) / ca-central-1
1.115367 USD/h 6.0512 USD/h
Dublin (IE) / eu-west-1
1.992233 USD/h 6.0512 USD/h
Mumbai (IN) / ap-south-1
1.127167 USD/h 6.2304 USD/h
London (GB) / eu-west-2
0.789033 USD/h 6.3712 USD/h
Paris (FR) / eu-west-3
- 6.3712 USD/h
Seoul (KR) / ap-northeast-2
1.2202 USD/h 6.4416 USD/h
Osaka (JP) / ap-northeast-3
2.212433 USD/h 6.4416 USD/h
Tokyo (JP) / ap-northeast-1
1.771133 USD/h 6.4512 USD/h
Frankfurt (DE) / eu-central-1
1.518867 USD/h 6.5472 USD/h
Sydney (AU) / ap-southeast-2
1.2401 USD/h 6.5824 USD/h
Singapore (SG) / ap-southeast-1
2.394833 USD/h 6.5824 USD/h
Jakarta (ID) / ap-southeast-3
- 6.5824 USD/h
Sao Paulo (BR) / sa-east-1
3.1528 USD/h 8.768 USD/h

Processor

vCPUs
64
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
64
CPU Speed
2.8 GHz
CPU Architecture
arm64
CPU Manufacturer
AWS
CPU Model
Neoverse-V2
CPU L1D Cache
64 KiB
CPU L1D Cache Total
4 MiB
CPU L1I Cache
64 KiB
CPU L1I Cache Total
4 MiB
CPU L2 Cache
2 MiB
CPU L2 Cache Total
128 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
63.9
Scalability
99.84

System Resources and Accelerators

MEMORY
Memory Amount
512 GiB
Memory Amount Actual
504 GiB
GPU
GPU Count
0
GPU Memory Min
0 MiB
GPU Memory Total
0 MiB
GPUs
    STORAGE
    Storage Size
    15000 GB
    Storage Type
    nvme ssd
    Storages
    • 3750 GB nvme ssd
    • 3750 GB nvme ssd
    • 3750 GB nvme ssd
    • 3750 GB nvme ssd
    NETWORK
    Network Speed Baseline
    37.5 Gbps
    Network Speed Max
    37.5 Gbps
    Network Storage Speed Baseline
    20 Gbps
    Network Storage Speed Max
    20 Gbps
    Inbound Traffic
    0 GB/month
    Outbound Traffic
    0 GB/month
    IPv4
    0

    Server Description

    An arm64 storage-optimized platform featuring dedicated cores, massive local NVMe SSD capacity, and top-tier memory bandwidth for data-intensive workloads.

    Storage & DatabaseMemory Optimized

    The Amazon Web Services i8g.16xlarge is an arm64 storage-optimized server powered by 64 dedicated AWS Graviton Neoverse-V2 physical cores running at 2.8 GHz. It features 512.0 GB of RAM and 15000 GB of bundled local NVMe SSD storage, operating on the Nitro hypervisor with a 38 Gbps baseline network bandwidth. Benchmarks show top-tier multi-core performance, memory bandwidth, and database operations, though single-core metrics remain average. While text generation for small LLM models is weak, it achieves top-tier speeds for medium models. This hardware profile offers strong qualitative cost efficiency for data-intensive workloads. It is suited for high-throughput databases, Redis caching, software compilation, and multi-threaded data processing.

    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) 13,963,224 ops/sec 1,917,397 ops/sec 7.28 50.00% 50.00% +170.00%
    Redis RPS (pipeline=16, SET) 84,583,679 ops/sec 11,681,410 ops/sec 7.24 20.00% 20.00% +48.60%
    PassMark Memory Mark (composite) 3,389 2,418 1.4 10.00% 10.00% +3.42%
    Memory bandwidth (read, 16 MB ~ L3) 529,336 MB/sec 108,140 MB/sec 4.89 10.00% 10.00% +17.20%
    PassMark single-thread CPU 1,944 Mops/s 2,365 Mops/s 0.822 10.00% 10.00% -1.94%

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 1,894

    Geekbench Multi-Core

    Score: 25,917

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 44081
    Compression
    		 424922
    Encryption
    		 12054
    Extended Instructions
    		 56416
    Floating Point Maths
    		 387793
    Integer Maths
    		 333793
    Physics
    		 15963
    Prime Numbers
    		 679
    Single Threaded
    		 1944
    String Sorting
    		 293128

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 3389
    Database Operations
    		 47373
    Memory Latency
    		 47
    Memory Read Cached
    		 21158
    Memory Read Uncached
    		 20145
    Memory Write
    		 21294

    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.4xlarge 16128 GiB0
    i8g.8xlarge 32256 GiB0
    i8g.12xlarge 48384 GiB0
    i8g.24xlarge 96768 GiB0

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYGPUs

    i8g.16xlarge FAQs