r6gd.metal by Amazon Web Services

r6gd.metal is a Memory optimized [AWS Graviton processors] [Instance store volumes] Gen6 metal server offered by Amazon Web Services with 64 vCPUs, 512 GiB of memory and 3.8 TB of storage. The pricing starts at 0.3686 USD per hour.
64 vCPU
512 GiB Memory
3.8 TB Storage
Spare SCore
97,227
(All-cores)
1,523
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
r6gd.metal
Description
Memory optimized [AWS Graviton processors] [Instance store volumes] Gen6 metal
Family
r6gd
Hw Virt
Status
active
Observed At
2026-10-02T14:00:43.601869Z

Availability

REGION / IDSPOTONDEMAND
Mumbai (IN) / ap-south-1
0.606167 USD/h 2.3917 USD/h
Ohio (US) / us-east-2
0.630633 USD/h 3.6864 USD/h
Oregon (US) / us-west-2
1.109 USD/h 3.6864 USD/h
Northern Virgina (US) / us-east-1
0.92942 USD/h 3.6864 USD/h
Stockholm (SE) / eu-north-1
0.3891 USD/h 3.8912 USD/h
Quebec (CA) / ca-central-1
0.483767 USD/h 4.0448 USD/h
Aragón (ES) / eu-south-2
0.4096 USD/h 4.096 USD/h
Dublin (IE) / eu-west-1
1.6268 USD/h 4.096 USD/h
California (US) / us-west-1
0.4905 USD/h 4.16 USD/h
Paris (FR) / eu-west-3
0.583233 USD/h 4.3264 USD/h
London (GB) / eu-west-2
1.1137 USD/h 4.3264 USD/h
Frankfurt (DE) / eu-central-1
1.3324 USD/h 4.416 USD/h
Seoul (KR) / ap-northeast-2
0.7227 USD/h 4.4288 USD/h
Jakarta (ID) / ap-southeast-3
0.4448 USD/h 4.448 USD/h
Sydney (AU) / ap-southeast-2
0.711933 USD/h 4.448 USD/h
Tokyo (JP) / ap-northeast-1
0.8427 USD/h 4.448 USD/h
Singapore (SG) / ap-southeast-1
1.7787 USD/h 4.448 USD/h
Osaka (JP) / ap-northeast-3
1.09575 USD/h 4.4544 USD/h
Zurich (CH) / eu-central-2
0.891633 USD/h 4.8576 USD/h
Cape Town (ZA) / af-south-1
0.815567 USD/h 4.864 USD/h
Sao Paulo (BR) / sa-east-1
0.5837 USD/h 5.8368 USD/h

Processor

vCPUs
64
CPU Allocation
Dedicated
CPU Cores
64
CPU Speed
2.5 GHz
CPU Architecture
arm64
CPU Manufacturer
AWS
CPU Family
ARMv8
CPU Model
Neoverse-N1
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
1 MiB
CPU L2 Cache Total
64 MiB
CPU L3 Cache
32 MiB
CPU L3 Cache Total
32 MiB
CPU Flags
fp, asimd, evtstrm, aes, pmull, sha1, sha2, crc32, atomics, fphp, asimdhp, cpuid, asimdrdm, lrcpc, dcpop, asimddp, ssbs
Ecpus
63.8
Scalability
99.69

System Resources and Accelerators

MEMORY
Memory Amount
512 GiB
Memory Amount Actual
512 GiB
Memory Generation
DDR4
GPU
GPU Count
0
GPU Memory Min
0 MiB
GPU Memory Total
0 MiB
GPUs
    STORAGE
    Storage Size
    3800 GB
    Storage Type
    nvme ssd
    Storages
    • 1900 GB nvme ssd
    • 1900 GB nvme ssd
    NETWORK
    Network Speed Baseline
    25 Gbps
    Network Speed Max
    25 Gbps
    Network Storage Speed Baseline
    19 Gbps
    Network Storage Speed Max
    19 Gbps
    Inbound Traffic
    0 GB/month
    Outbound Traffic
    0 GB/month
    IPv4
    0

    Server Description

    A bare-metal, memory-optimized ARM server featuring dedicated physical cores, high-capacity local NVMe storage, and strong multi-core performance.

    Memory OptimizedStorage & DatabaseGeneral Purpose

    Amazon Web Services r6gd.metal is a bare-metal, memory-optimized server powered by 64 dedicated physical cores of the 64-bit ARMv8 AWS Graviton Neoverse-N1 processor running at 2.5 GHz. It is equipped with 512.0 GB of DDR4 memory, 3800 GB of local NVMe SSD instance storage, and a baseline network bandwidth of 25 Gbps. The server lacks GPU acceleration. Benchmarks indicate strong multi-core capabilities, highlighted by a stress-ng multi-core score of 97227.26 and strong cached memory bandwidth of 3792.89 GB/sec. It also excels in static web serving and Redis SET operations, achieving 74.12 million operations per second. However, single-core performance and LLM inference speeds are relatively weak. This bare-metal instance is highly suited for memory-intensive databases, caching layers, software compilation, and high-throughput web serving workloads that benefit from direct hardware access and local NVMe storage.

    Economics

    Average Price per Region

    Prices per Zone

    Lowest Prices

    Performance

    Workload Profiles

    2.3Score
    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) 7,048,421 ops/sec 1,916,704 ops/sec 3.7 50.00% 50.00% +92.00%
    Redis RPS (pipeline=16, SET) 41,241,158 ops/sec 11,642,227 ops/sec 3.4 20.00% 20.00% +28.00%
    PassMark Memory Mark (composite) 1,865 2,418 0.79 10.00% 10.00% -2.30%
    Memory bandwidth (read, 16 MB ~ L3) 173,108 MB/sec 108,322 MB/sec 1.5 10.00% 10.00% +4.10%
    PassMark single-thread CPU 1,115 Mops/s 2,365 Mops/s 0.46 10.00% 10.00% -7.50%

    Memory Bandwidth

    Compression

    OpenSSL

    Geekbench Single-Core

    Score: 985

    Geekbench Multi-Core

    Score: 14,015

    Passmark CPU Scores

    BENCHMARKSCORE
    Mark
    28153
    Compression
    305773
    Encryption
    8700
    Extended Instructions
    39932
    Floating Point Maths
    192113
    Integer Maths
    253191
    Physics
    4121
    Prime Numbers
    253
    Single Threaded
    1115
    String Sorting
    175422

    Passmark Memory Scores

    BENCHMARKSCORE
    Memory Mark
    1865
    Database Operations
    20537
    Memory Latency
    69
    Memory Read Cached
    9511
    Memory Read Uncached
    9233
    Memory Write
    12442

    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
    r6gd.medium 18 GiB0
    r6gd.large 216 GiB0
    r6gd.xlarge 432 GiB0
    r6gd.2xlarge 864 GiB0
    r6gd.4xlarge 16128 GiB0
    r6gd.8xlarge 32256 GiB0
    r6gd.12xlarge 48384 GiB0

    Similar Servers

    INSTANCEVENDORvCPUsMEMORYGPUs

    r6gd.metal FAQs