gr6.8xlarge

Amazon EC2 · Gr6 family

The gr6.8xlarge is a gpu & accelerated Amazon EC2 instance type with 32 vCPUs and 256 GiB of memory, 1 × NVIDIA L4, running on AMD EPYC 7R13 Processor with 25 Gigabit networking, starting at $2.446 per hour on demand.

gpu & acceleratedx86-64amdgpu
vCPUs
32

dedicated

memory
256 GiB

8 GiB per vCPU

gpu
1× L4

24 GiB total

on-demand
$2.446

$1,786/mo · us-east-1

spot
$0.3131

−87% vs on-demand

1-yr reserved
$1.593

−35% vs on-demand

gr6.8xlarge 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$2.446$0.3131$1.593$1.123
US East (Ohio)us-east-2cheapestNorth America$2.446$0.3129$1.593$1.123
US West (Oregon)us-west-2cheapestNorth America$2.446$0.3169$1.593$1.123
EU (Spain)eu-south-2Europe$2.578–$1.678$1.183
EU (Stockholm)eu-north-1Europe$2.595–$1.689$1.191
Canada (Central)ca-central-1North America$2.716–$1.768$1.247
Asia Pacific (Mumbai)ap-south-1Asia$2.938–$1.912$1.348
Asia Pacific (Seoul)ap-northeast-2Asia$3.008–$1.958$1.381
EU (Frankfurt)eu-central-1Europe$3.059–$1.992$1.404
Asia Pacific (Malaysia)ap-southeast-5Asia$3.082–$2.006$1.414
AWS GovCloud (US-East)us-gov-east-1North America$3.084–$2.007$1.415
AWS GovCloud (US)us-gov-west-1North America$3.084–$2.007$1.415
EU (Paris)eu-west-3Europe$3.105–$2.022$1.425
EU (London)eu-west-2Europe$3.106–$2.022$1.425
Asia Pacific (Sydney)ap-southeast-2Oceania$3.181–$2.071$1.46
EU (Zurich)eu-central-2Europe$3.441–$2.24$1.579
Asia Pacific (Tokyo)ap-northeast-1Asia$3.548–$2.31$1.629
South America (Sao Paulo)sa-east-1South America$4.159–$2.707$1.909

Specifications

compute

vCPUs
32
Memory
256 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
900 GB NVME (2 disks)
Storage detail
2 x 450 GB NVMe SSD
Network
25 Gigabit
Peak bandwidth
25 Gbps

accelerators

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

aws details

API name
gr6.8xlarge
Family
Gr6
Category
GPU & accelerated
Generation
Current
Regions
18 (Asia, Europe, North America, Oceania, South America)
Cheapest region
US East (N. Virginia) · $2.446/hr
Dedicated EBS throughput
16000 Mbps
Enhanced networking
Yes
Normalization size factor
1.59
Processor features
AMD Turbo; AVX; AVX2
Spot interruption rate (us-east-1)
10-15%
Spot savings vs on-demand (us-east-1)
56%

gr6.8xlarge 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 gr6.8xlarge
AWSgr6.8xlarge32256 GiB1 × NVIDIA L4$2.446–
AzureNG32adms V620 v1176 GiB (1.5× less) · AMD Radeon Pro V62032176 GiB1 × AMD Radeon Pro V620$3.302+35%
Google Cloudg2-standard-32128 GiB (2× less)32128 GiB1 × NVIDIA L4$1.734-29%

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

gr6.8xlarge FAQ

How much does gr6.8xlarge cost?

gr6.8xlarge costs $2.446 per hour on demand with Linux in US East (N. Virginia) (us-east-1), about $1,786 per month. Across 18 regions the Linux on-demand price ranges from $2.446 in US East (N. Virginia) to $4.159 in South America (Sao Paulo). Spot capacity costs $0.3131 per hour (87% less), but can be reclaimed. A 1-yr Reserved commitment brings it to $1.593 per hour. With Windows it costs $3.918 per hour.

How many vCPUs and how much memory does gr6.8xlarge have?

gr6.8xlarge has 32 vCPUs and 256 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 gr6.8xlarge have?

gr6.8xlarge has 1 × NVIDIA L4 with 24 GiB of accelerator memory in total.

What are the equivalents of gr6.8xlarge on other clouds?

The closest matches by vCPU, memory, CPU architecture, accelerator and instance class are on Azure, NG32adms V620 v1 (32 vCPU, 176 GiB, $3.302/hour in East US 2); on Google Cloud, g2-standard-32 (32 vCPU, 128 GiB, $1.734/hour in Iowa).