g5g.4xlarge specs and pricing | AWS

Amazon EC2 instance g5g.4xlarge with 16 vCPUs, 32 GiB RAM and 1 x NVIDIA T4g 16 GiB. Available in 7 regions starting from $604.44 per month.

Instance Type	g5g.4xlarge
Instance Family	GPU instance
Details	Machine Learning (ML), 3D visualizations, graphics-heavy remote workstations, 3D rendering, application streaming, video encoding, and server-side graphics tasks. g – GPU (Graphics Processing Unit) 5 – Generation g – AWS Graviton processor 4xlarge – Size
vCPUs	16
Memory	32 GiB
CPU Architecture	arm64
Processor	AWS Graviton2 Processor
Clock Speed	2.5 GHz
Threads Per Core	1

Accelerators
GPU	yes
GPU Name	T4g
GPU Manufacturer	NVIDIA
GPUs	1
GPU Memory	16 GiB
GPU Total Memory	16 GiB
Inference Accelerator	no
Accelerator Memory	16 GiB
FPGA	no

Instances
Sizes	g5g.xlarge, g5g.2xlarge, g5g.4xlarge, g5g.8xlarge, g5g.16xlarge, g5g.metal
Variants	g5.4xlarge

Free Tier	no
Burstable	no
Hibernation	no
Instance Storage	EBS only

EBS (Elastic Block Store)
EBS Optimized	default
Encryption	supported
NVMe	required
Dedicated Throughput	4750 MBps
Optimized Baseline Bandwidth	4750 Mbps
Optimized Baseline Throughput	593.75 Mbps
Optimized Baseline Performance	20000 IOPS
Optimized Max Performance	20000 IOPS
Optimized Max Bandwidth	4750 Mbps
Optimized Max Throughput	593.75 Mbps

Networking
Networking Performance	Up to 10 Gigabit
Enhanced Networking	yes
Max Interfaces	8
Max Cards	1
IPv4 Addresses per Interface	30
IPv6 Addresses per Interface	30
IPv6 Support	yes
ENA Support	required
EFA Support	no
Encryption in Transit Support	no
ENA SRD Support	no

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
US	US East (Virginia)	us-east-1	compare	0.8280
US	US West (Oregon)	us-west-2	compare	0.8280
Europe	Europe (Spain)	eu-south-2	compare	0.9240
Hidden	Hidden	hidden-1	compare	1.0185
Hidden	Hidden	hidden-2	compare	1.0358
Hidden	Hidden	hidden-3	compare	1.1176
Hidden	Hidden	hidden-4	compare	1.1586

Best AI models you can run on this instance

Top open-weight chat models ranked by Intelligence Index that fit in g5g.4xlarge'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 4B	Alibaba	27.1#190	4B	—	10 GB
MiniCPM5 1B	Openbmb	18.2#292	1B	—	2 GB
MiniCPM5 1B Non-Reasoning	Openbmb	17.9#298	1B	—	2 GB
7 more models fit on g5g.4xlarge 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 %
g4ad.4xlarge	US East (Virginia) (us-east-1)	16	64	Radeon Pro V520	0.8670	5%
g4dn.4xlarge	US East (Virginia) (us-east-1)	16	64	T4	1.2040	45%
g6.4xlarge	US East (Virginia) (us-east-1)	16	64	L4	1.3232	60%
gr6.4xlarge	US East (Virginia) (us-east-1)	16	128	L4	1.5392	86%
g5.4xlarge	US East (Virginia) (us-east-1)	16	64	A10G	1.6240	96%