gr6.4xlarge

Amazon EC2 · Gr6 family

The gr6.4xlarge is a gpu & accelerated Amazon EC2 instance type with 16 vCPUs and 128 GiB of memory, 1 × NVIDIA L4, running on AMD EPYC 7R13 Processor with up to 25 Gigabit networking, starting at $1.539 per hour on demand.

gpu & acceleratedx86-64amdgpu
vCPUs
16

dedicated

memory
128 GiB

8 GiB per vCPU

gpu
1× L4

24 GiB total

on-demand
$1.539

$1,124/mo · us-east-1

spot
$0.2002

−87% vs on-demand

1-yr reserved
$1.002

−35% vs on-demand

gr6.4xlarge price by region

18 regions · hourly list prices in USD · On-demand · Spot · 1-yr Reserved · 3-yr Reserved

US East (N. Virginia)us-east-1cheapestreferenceNorth America$1.539$0.2002$1.002$0.7065
US East (Ohio)us-east-2cheapestNorth America$1.539$0.1981$1.002$0.7065
US West (Oregon)us-west-2cheapestNorth America$1.539$0.2057$1.002$0.7065
EU (Spain)eu-south-2Europe$1.622–$1.056$0.7444
EU (Stockholm)eu-north-1Europe$1.633–$1.063$0.7494
Canada (Central)ca-central-1North America$1.709–$1.113$0.7844
Asia Pacific (Mumbai)ap-south-1Asia$1.848–$1.203$0.8484
Asia Pacific (Seoul)ap-northeast-2Asia$1.893–$1.232$0.8687
EU (Frankfurt)eu-central-1Europe$1.925–$1.253$0.8835
Asia Pacific (Malaysia)ap-southeast-5Asia$1.939–$1.262$0.8899
AWS GovCloud (US-East)us-gov-east-1North America$1.94–$1.263$0.8905
AWS GovCloud (US)us-gov-west-1North America$1.94–$1.263$0.8905
EU (Paris)eu-west-3Europe$1.954–$1.272$0.8968
EU (London)eu-west-2Europe$1.954–$1.272$0.8968
Asia Pacific (Sydney)ap-southeast-2Oceania$2.001–$1.303$0.9186
EU (Zurich)eu-central-2Europe$2.165–$1.409$0.9937
Asia Pacific (Tokyo)ap-northeast-1Asia$2.232–$1.453$1.025
South America (Sao Paulo)sa-east-1South America$2.616–$1.703$1.201

Specifications

compute

vCPUs
16
Memory
128 GiB
Memory per vCPU
8 GiB
Processor
AMD EPYC 7R13 Processor
CPU vendor
AMD
Architecture
x86-64
Clock speed
2.6 GHz
Burstable CPU
No

storage & network

Local storage
600 GB NVME
Storage detail
1 x 600 GB NVMe SSD
Network
Up to 25 Gigabit
Peak bandwidth
25 Gbps

accelerators

Count
1
Memory (total)
24 GiB
Architecture
Ada Lovelace
Vendor
NVIDIA

aws details

API name
gr6.4xlarge
Family
Gr6
Category
GPU & accelerated
Generation
Current
Regions
18 (Asia, Europe, North America, Oceania, South America)
Cheapest region
US East (N. Virginia) · $1.539/hr
Dedicated EBS throughput
8000 Mbps
Enhanced networking
Yes
Normalization size factor
1
Processor features
AMD Turbo; AVX; AVX2
Spot interruption rate (us-east-1)
>20%
Spot savings vs on-demand (us-east-1)
41%

gr6.4xlarge equivalents on other clouds

closest match by vCPU, memory, CPU architecture, accelerator and class · Linux on-demand in each provider's reference region

compare side by side→
ProviderInstancevCPUMemoryProcessorOn-demandvs gr6.4xlarge
AWSgr6.4xlarge16128 GiB1 × NVIDIA L4$1.539–
AzureNC16as T4 v3110 GiB (1.2× less) · NVIDIA T416110 GiB1 × NVIDIA T4$1.204-22%
NC16ads A10 v4220 GiB (1.72×) · NVIDIA A1016220 GiB1 × NVIDIA A10$2.20+43%
Google Cloudg2-standard-1664 GiB (2× less)1664 GiB1 × NVIDIA L4$1.147-25%
g2-standard-3232 vCPU (2×)32128 GiB1 × NVIDIA L4$1.734+13%

Gr6 family sizes

all about Gr6→
SizevCPUMemoryAcceleratorLocal storageOn-demandMonthlySpot1-yr
gr6.4xlarge16128 GiB1 × NVIDIA L4600 GB NVME$1.539$1,124$0.2002$1.002
gr6.8xlarge32256 GiB1 × NVIDIA L4900 GB NVME (2 disks)$2.446$1,786$0.3131$1.593

gr6.4xlarge FAQ

How much does gr6.4xlarge cost?

gr6.4xlarge costs $1.539 per hour on demand with Linux in US East (N. Virginia) (us-east-1), about $1,124 per month. Across 18 regions the Linux on-demand price ranges from $1.539 in US East (N. Virginia) to $2.616 in South America (Sao Paulo). Spot capacity costs $0.2002 per hour (87% less), but can be reclaimed. A 1-yr Reserved commitment brings it to $1.002 per hour. With Windows it costs $2.275 per hour.

How many vCPUs and how much memory does gr6.4xlarge have?

gr6.4xlarge has 16 vCPUs and 128 GiB of memory (8 GiB per vCPU), running on AMD EPYC 7R13 Processor. It is a gpu & accelerated instance type in the Gr6 family.

What GPU does gr6.4xlarge have?

gr6.4xlarge has 1 × NVIDIA L4 with 24 GiB of accelerator memory in total.

What are the equivalents of gr6.4xlarge on other clouds?

The closest matches by vCPU, memory, CPU architecture, accelerator and instance class are on Azure, NC16as T4 v3 (16 vCPU, 110 GiB, $1.204/hour in East US); on Google Cloud, g2-standard-16 (16 vCPU, 64 GiB, $1.147/hour in Iowa).