g4dn.8xlarge


Amazon EC2 instance g4dn.8xlarge with 32 vCPUs, 128 GiB RAM and 1 x NVIDIA T4 16 GiB. Available in 23 regions starting from $1588.48 per month. A -37% cheaper alternative is available.
Instance Typeg4dn.8xlarge
Instance FamilyGPU instance
DetailsMachine Learning (ML), 3D visualizations, graphics-heavy remote workstations, 3D rendering, application streaming, video encoding, and server-side graphics tasks.

g – GPU (Graphics Processing Unit)
4 – Generation
d – Instance store volume
n – Network and EBS optimized
8xlarge – Size
vCPUs32
Memory128 GiB
CPU Architecturex86_64
ProcessorIntel Xeon Family
Clock Speed2.5 GHz
Threads Per Core2
Accelerators
GPUyes
GPU NameT4
GPU ManufacturerNVIDIA
GPUs1
GPU Memory16 GiB
GPU Total Memory16 GiB
Inference Acceleratorno
Accelerator Memory16 GiB
FPGAno
Instances
Sizesg4dn.xlarge, g4dn.2xlarge, g4dn.4xlarge, g4dn.8xlarge, g4dn.12xlarge, g4dn.16xlarge, g4dn.metal
Variantsg4ad.8xlarge
SageMakerml.g4dn.8xlarge
Free Tierno
Burstableno
Hibernationno
Instance Storage900 GB NVMe SSD
EBS (Elastic Block Store)
EBS Optimizeddefault
Encryptionsupported
NVMerequired
Dedicated Throughput7000 MBps
Optimized Baseline Bandwidth9500 Mbps
Optimized Baseline Throughput1187.5 Mbps
Optimized Baseline Performance40000 IOPS
Optimized Max Performance40000 IOPS
Optimized Max Bandwidth9500 Mbps
Optimized Max Throughput1187.5 Mbps
Networking
Networking Performance50 Gigabit
Enhanced Networkingyes
Max Interfaces4
Max Cards1
IPv4 Addresses per Interface15
IPv6 Addresses per Interface15
IPv6 Supportyes
ENA Supportrequired
EFA Supportyes
EFA Max Interfaces1
Encryption in Transit Supportyes
ENA SRD Supportno

Regional Availability

US
GovCloud (US-East) / us-gov-east-1
GovCloud (US-West) / us-gov-west-1
US East (Ohio) / us-east-2
US East (Virginia) / us-east-1
US West (N. California) / us-west-1
US West (Oregon) / us-west-2
Central America
Mexico (Central) / mx-central-1
Canada
Canada (Central) / ca-central-1
Canada West (Calgary) / ca-west-1
Europe
Europe (Ireland) / eu-west-1
Europe (London) / eu-west-2
Europe (Frankfurt) / eu-central-1
Europe (Milan) / eu-south-1
Europe (Paris) / eu-west-3
Europe (Spain) / eu-south-2
Europe (Stockholm) / eu-north-1
Europe (Zurich) / eu-central-2
Africa
Africa (Cape Town) / af-south-1
South America
South America (São Paulo) / sa-east-1
Asia Pacific
Asia Pacific (Hong Kong) / ap-east-1
Asia Pacific (Hyderabad) / ap-south-2
Asia Pacific (Jakarta) / ap-southeast-3
Asia Pacific (Malaysia) / ap-southeast-5
Asia Pacific (Melbourne) / ap-southeast-4
Asia Pacific (Mumbai) / ap-south-1
Asia Pacific (New Zealand) / ap-southeast-6
Asia Pacific (Osaka) / ap-northeast-3
Asia Pacific (Seoul) / ap-northeast-2
Asia Pacific (Singapore) / ap-southeast-1
Asia Pacific (Sydney) / ap-southeast-2
Asia Pacific (Taipei) / ap-east-2
Asia Pacific (Thailand) / ap-southeast-7
Asia Pacific (Tokyo) / ap-northeast-1
Middle East
Israel (Tel Aviv) / il-central-1
Middle East (Bahrain) / me-south-1
Middle East (UAE) / me-central-1

Regional Prices

US Dollar ($)
Per Hour
Linux
Shared Tenancy
On Demand
Geography
Region Name
Region
Savings Options
Instance Price
USUS East (Virginia)us-east-1compare2.1760
USUS East (Ohio)us-east-2compare2.1760
USUS West (Oregon)us-west-2compare2.1760
HiddenHiddenhidden-1compare2.3080
HiddenHiddenhidden-2compare2.3950
HiddenHiddenhidden-3compare2.4160
HiddenHiddenhidden-4compare2.4260
HiddenHiddenhidden-5compare2.5440
HiddenHiddenhidden-6compare2.5460
HiddenHiddenhidden-7compare2.5470
HiddenHiddenhidden-8compare2.6110
HiddenHiddenhidden-9compare2.6690
HiddenHiddenhidden-10compare2.6770
HiddenHiddenhidden-11compare2.7200
HiddenHiddenhidden-12compare2.7430
HiddenHiddenhidden-13compare2.7430
HiddenHiddenhidden-14compare2.8300
HiddenHiddenhidden-15compare2.8870
HiddenHiddenhidden-16compare2.9380
HiddenHiddenhidden-17compare2.9380
HiddenHiddenhidden-18compare3.0450
HiddenHiddenhidden-19compare3.3510
HiddenHiddenhidden-20compare3.6980
Activate subscription to see all regions and unlock awesome features  

Best AI models you can run on this instance

Top open-weight chat models ranked by Intelligence Index that fit in g4dn.8xlarge's 16 GB of GPU memory. VRAM is estimated from the parameter count at the selected quantization, so treat it as guidance rather than a guarantee.

Chat Models
FP16 (full precision)
Model
Creator
Intelligence
Total params
Active params
~VRAM
Qwen3.5 4BAlibaba logoAlibaba27.1#1904B—10 GB
MiniCPM5 1BOpenbmb18.2#2921B—2 GB
MiniCPM5 1B Non-ReasoningOpenbmb17.9#2981B—2 GB
7 more models fit on g4dn.8xlarge
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Similar Alternative Instances

Find Similar Instances In:
Instance Type
Region
vCPUs
Memory (GiB)
GPU Name
Instance Price
Price Diff %
g5g.8xlargeUS East (Virginia) (us-east-1)3264T4g1.3720-37%
g4ad.8xlargeUS East (Virginia) (us-east-1)32128Radeon Pro V5201.7340-20%
g6.8xlargeUS East (Virginia) (us-east-1)32128L42.0144-7%
g5.8xlargeUS East (Virginia) (us-east-1)32128A10G2.448012%
gr6.8xlargeUS East (Virginia) (us-east-1)32256L42.446412%
Select your cookie preferences
We use cookies and similar tools to enhance your experience, provide our services, and make improvements. Approved third parties also use these tools to certain site features. More details available here Cookie Policy