m8gd.4xlarge by Amazon Web Services

m8gd.4xlarge is a General purpose [AWS Graviton processors] [Instance store volumes] Gen8 4xlarge server offered by Amazon Web Services with 16 vCPUs, 64 GiB of memory and 950 GB of storage. The pricing starts at 0.0989 USD per hour.
16 vCPU
64 GiB Memory
950 GB Storage
Spare SCore
27,307
(All-cores)
1,707
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
m8gd.4xlarge
Description
General purpose [AWS Graviton processors] [Instance store volumes] Gen8 4xlarge
Family
m8gd
Hw Virt
Status
active
Observed At
2026-10-25T01:22:14.265529

Availability

REGION / IDSPOTONDEMAND
Mumbai (IN) / ap-south-1
0.224 USD/h 0.6134 USD/h
Ohio (US) / us-east-2
0.213033 USD/h 0.9226 USD/h
Oregon (US) / us-west-2
0.2867 USD/h 0.9226 USD/h
Northern Virgina (US) / us-east-1
0.62722 USD/h 0.9226 USD/h
(MX) / mx-central-1
0.54055 USD/h 0.9686 USD/h
(MY) / ap-southeast-5
0.287833 USD/h 0.9786 USD/h
Stockholm (SE) / eu-north-1
0.1022 USD/h 0.9798 USD/h
Aragón (ES) / eu-south-2
0.1029 USD/h 1.0288 USD/h
Quebec (CA) / ca-central-1
0.326967 USD/h 1.0288 USD/h
Dublin (IE) / eu-west-1
0.4336 USD/h 1.0288 USD/h
London (GB) / eu-west-2
0.290925 USD/h 1.0696 USD/h
Paris (FR) / eu-west-3
0.3508 USD/h 1.0778 USD/h
California (US) / us-west-1
0.6038 USD/h 1.0859 USD/h
Frankfurt (DE) / eu-central-1
0.397067 USD/h 1.1104 USD/h
Singapore (SG) / ap-southeast-1
0.416367 USD/h 1.1512 USD/h
Melbourne (AU) / ap-southeast-4
0.22965 USD/h 1.1594 USD/h
Sydney (AU) / ap-southeast-2
0.3929 USD/h 1.1594 USD/h
Tokyo (JP) / ap-northeast-1
0.417867 USD/h 1.192 USD/h
Sao Paulo (BR) / sa-east-1
0.605033 USD/h 1.4696 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 Family
ARMv9
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
64 GiB
Memory Amount Actual
63 GiB
ACCELERATORS
Accelerator Count
0
Accelerator Memory Min
0 MiB
Accelerator Memory Total
0 MiB
Accelerators
    STORAGE
    Storage Size
    950 GB
    Storage Type
    nvme ssd
    Storages
    • 950 GB nvme ssd
    NETWORK
    Network Speed Baseline
    7.5 Gbps
    Network Speed Max
    15 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 general-purpose instance featuring dedicated physical cores, top-tier memory performance, and high-speed local NVMe SSD storage.

    General PurposeStorage & Database

    Amazon Web Services m8gd.4xlarge is a general-purpose instance powered by 16 dedicated ARMv9 Neoverse-V2 cores running at 2.8 GHz. Built on the AWS Nitro hypervisor, it features 64.0 GB of RAM and 950 GB of local NVMe SSD instance storage. The instance delivers strong memory performance, with its Passmark memory score ranking in the top 10% and large-block memory bandwidth in the top 25%. While single-core and multi-core CPU benchmarks generally align with average mid-tier performance, its multi-threaded decompression and database operations show strong results. Lacking a GPU, it is not optimized for heavy machine learning tasks, as evidenced by lower LLM prompt processing speeds. However, its balanced resource allocation and high-speed local storage make it highly cost-efficient for database hosting, web serving, and general-purpose enterprise workloads.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    1.7Score
    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) 3,633,705 ops/sec 1,919,289 ops/sec 1.9 50.00% 50.00% +38.00%
    Redis RPS (pipeline=16, SET) 22,409,634 ops/sec 11,728,058 ops/sec 1.8 20.00% 20.00% +12.00%
    PassMark Memory Mark (composite) 3,296 2,416 1.4 10.00% 10.00% +3.40%
    Memory bandwidth (read, 16 MB ~ L3) 333,761 MB/sec 108,466 MB/sec 3 10.00% 10.00% +12.00%
    PassMark single-thread CPU 1,945 Mops/s 2,365 Mops/s 0.79 10.00% 10.00% -2.30%

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 1,888

    Geekbench Multi-Core

    Score: 15,912

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    		 14,610
    Compression
    		 106,395
    Encryption
    		 3,030
    Extended Instructions
    		 14,720
    Floating Point Maths
    		 97,018
    Integer Maths
    		 83,511
    Physics
    		 4,903
    Prime Numbers
    		 265
    Single Threaded
    		 1,945
    String Sorting
    		 74,267

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    		 3,296
    Database Operations
    		 24,155
    Memory Latency
    		 47
    Memory Read Cached
    		 21,187
    Memory Read Uncached
    		 19,991
    Memory Write
    		 21,288

    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
    m8gd.medium 14 GiB0
    m8gd.large 28 GiB0
    m8gd.xlarge 416 GiB0
    m8gd.2xlarge 832 GiB0
    m8gd.8xlarge 32128 GiB0
    m8gd.12xlarge 48192 GiB0
    m8gd.16xlarge 64256 GiB0

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYAccelerators

    m8gd.4xlarge FAQs