g4ad.16xlarge specs and pricing | AWS

Amazon EC2 instance g4ad.16xlarge with 64 vCPUs, 256 GiB RAM and 4 x AMD Radeon Pro V520 8 GiB. Available in 8 regions starting from $2531.64 per month. A -21% cheaper alternative is available.

Instance Type	g4ad.16xlarge
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) 4 – Generation a – AMD processor d – Instance store volume 16xlarge – Size
vCPUs	64
Memory	256 GiB
CPU Architecture	x86_64
Processor	AMD EPYC 7R32
Clock Speed	3 GHz
Threads Per Core	2

Accelerators
GPU	yes
GPU Name	Radeon Pro V520
GPU Manufacturer	AMD
GPUs	4
GPU Memory	8 GiB
GPU Total Memory	32 GiB
Inference Accelerator	no
Accelerator Memory	32 GiB
FPGA	no

Instances
Sizes	g4ad.xlarge, g4ad.2xlarge, g4ad.4xlarge, g4ad.8xlarge, g4ad.16xlarge
Variants	g4dn.16xlarge

Free Tier	no
Burstable	no
Hibernation	no
Instance Storage	2400 GB NVMe SSD

EBS (Elastic Block Store)
EBS Optimized	default
Encryption	supported
NVMe	required
Dedicated Throughput	6000 MBps
Optimized Baseline Bandwidth	6300 Mbps
Optimized Baseline Throughput	787.5 Mbps
Optimized Baseline Performance	26667 IOPS
Optimized Max Performance	26667 IOPS
Optimized Max Bandwidth	6300 Mbps
Optimized Max Throughput	787.5 Mbps

Networking
Networking Performance	25 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	yes
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	3.4680
US	US East (Ohio)	us-east-2	compare	3.4680
US	US West (Oregon)	us-west-2	compare	3.4680
Hidden	Hidden	hidden-1	compare	3.8720
Hidden	Hidden	hidden-2	compare	3.8720
Hidden	Hidden	hidden-3	compare	4.0560
Hidden	Hidden	hidden-4	compare	4.3360
Hidden	Hidden	hidden-5	compare	4.6800

Best AI models you can run on this instance

Top open-weight chat models ranked by Intelligence Index that fit in g4ad.16xlarge's 32 GB of GPU memory, assuming the model is sharded across all 4 GPUs. 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 9B	Alibaba	32.4#146	9B	—	22 GB
Gemma 4 12B	Google	29.2#173	12B	—	29 GB
Qwen3.5 4B	Alibaba	27.1#190	4B	—	10 GB
7 more models fit on g4ad.16xlarge 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.16xlarge	US East (Virginia) (us-east-1)	64	128	T4g	2.7440	-21%
g4dn.12xlarge	US East (Virginia) (us-east-1)	48	192	T4	3.9120	13%
g3.16xlarge	US East (Virginia) (us-east-1)	64	488		4.5600	31%
g6.12xlarge	US East (Virginia) (us-east-1)	48	192	L4	4.6016	33%
g5.12xlarge	US East (Virginia) (us-east-1)	48	192	A10G	5.6720	64%