g7e.48xlarge specs and pricing | AWS

Amazon EC2 instance g7e.48xlarge with 192 vCPUs, 2048 GiB RAM and 8 x NVIDIA RTX PRO Server 6000 96 GiB. Available in 7 regions starting from $24195.35 per month. A -100% cheaper alternative is available.

Instance Type	g7e.48xlarge
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) 7 – Generation e – Extra storage or memory 48xlarge – Size
vCPUs	192
Memory	2048 GiB
CPU Architecture	x86_64
Processor	Intel Xeon Scalable (Emerald Rapids)
Clock Speed	2.4 GHz
Threads Per Core	2

Accelerators
GPU	yes
GPU Name	RTX PRO Server 6000
GPU Manufacturer	NVIDIA
GPUs	8
GPU Memory	96 GiB
GPU Total Memory	768 GiB
Inference Accelerator	no
Accelerator Memory	768 GiB
FPGA	no

Instances
Sizes	g7e.2xlarge, g7e.4xlarge, g7e.8xlarge, g7e.12xlarge, g7e.24xlarge, g7e.48xlarge
Generations	g6e.48xlarge, g7e.48xlarge
SageMaker	ml.g7e.48xlarge

Free Tier	no
Burstable	no
Hibernation	no
Instance Storage	4 x 3800 NVMe SSD

EBS (Elastic Block Store)
EBS Optimized	default
Encryption	supported
NVMe	required
Dedicated Throughput	100000 MBps
Optimized Baseline Bandwidth	100000 Mbps
Optimized Baseline Throughput	12500 Mbps
Optimized Baseline Performance	400000 IOPS
Optimized Max Performance	400000 IOPS
Optimized Max Bandwidth	100000 Mbps
Optimized Max Throughput	12500 Mbps

Networking
Networking Performance	1600 Gigabit
Enhanced Networking	yes
Max Interfaces	40
Max Cards	4
IPv4 Addresses per Interface	64
IPv6 Addresses per Interface	64
IPv6 Support	yes
ENA Support	required
EFA Support	yes
EFA Max Interfaces	4
Encryption in Transit Support	yes
ENA SRD Support	yes

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	33.1443
US	US East (Ohio)	us-east-2	compare	33.1443
US	US West (Oregon)	us-west-2	compare	33.1443
Hidden	Hidden	hidden-1	compare	34.9254
Hidden	Hidden	hidden-2	compare	40.7492
Hidden	Hidden	hidden-3	compare	48.0691
Hidden	Hidden	hidden-4	compare	57.6069

Best AI models you can run on this instance

Top open-weight chat models ranked by Intelligence Index that fit in g7e.48xlarge's 768 GB of GPU memory, assuming the model is sharded across all 8 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
DeepSeek V4 Flash	DeepSeek	40.3#28	158B	—	379 GB
MiniMax M2.7	MiniMax	38.1#42	229B	—	549 GB
Qwen3.6 27B	Alibaba	37.1#51	27B	—	65 GB
7 more models fit on g7e.48xlarge 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 %
p5.48xlarge	US East (Virginia) (us-east-1)	192	2048	H100	n/a	-100%
p4d.24xlarge	US East (Virginia) (us-east-1)	96	1152	A100	21.9576	-34%
p4de.24xlarge	US East (Virginia) (us-east-1)	96	1152	A100	27.4471	-17%
g6e.48xlarge	US East (Virginia) (us-east-1)	192	1536	L40S	30.1312	-9%
p5en.48xlarge	US East (Virginia) (us-east-1)	192	2048	H200	63.2960	91%