p3dn.24xlarge specs and pricing | AWS

Amazon EC2 instance p3dn.24xlarge with 96 vCPUs, 768 GiB RAM and 8 x NVIDIA V100 32 GiB. Available in 6 regions starting from $22784.76 per month. A -57% cheaper alternative is available.

Instance Type	p3dn.24xlarge
Instance Family	GPU instance
Details	GPU intensive tasks like machine/deep learning, high-performance computing p – Performance / GPU (Graphics Processing Unit) accelerated 3 – Generation d – Instance store volume n – Network and EBS optimized 24xlarge – Size
vCPUs	96
Memory	768 GiB
CPU Architecture	x86_64
Processor	Intel Xeon Platinum 8175 (Skylake)
Clock Speed	2.5 GHz
Threads Per Core	2

Accelerators
GPU	yes
GPU Name	V100
GPU Manufacturer	NVIDIA
GPUs	8
GPU Memory	32 GiB
GPU Total Memory	256 GiB
Inference Accelerator	no
Accelerator Memory	256 GiB
FPGA	no

Instances
Sizes	p3dn.24xlarge
SageMaker	ml.p3dn.24xlarge

Free Tier	no
Burstable	no
Hibernation	no
EC2 Compute Units	337
Instance Storage	2 x 900 NVMe SSD

EBS (Elastic Block Store)
EBS Optimized	default
Encryption	supported
NVMe	required
Dedicated Throughput	14000 MBps
Optimized Baseline Bandwidth	19000 Mbps
Optimized Baseline Throughput	2375 Mbps
Optimized Baseline Performance	80000 IOPS
Optimized Max Performance	80000 IOPS
Optimized Max Bandwidth	19000 Mbps
Optimized Max Throughput	2375 Mbps

Networking
Networking Performance	100 Gigabit
Enhanced Networking	yes
Max Interfaces	15
Max Cards	1
IPv4 Addresses per Interface	50
IPv6 Addresses per Interface	50
IPv6 Support	yes
ENA Support	required
EFA Support	yes
EFA Max Interfaces	1
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	31.2120
US	US West (Oregon)	us-west-2	compare	31.2120
Europe	Europe (Ireland)	eu-west-1	compare	33.7110
Hidden	Hidden	hidden-1	compare	37.4540
Hidden	Hidden	hidden-2	compare	37.4540
Hidden	Hidden	hidden-3	compare	42.7830

Best AI models you can run on this instance

Top open-weight chat models ranked by Intelligence Index that fit in p3dn.24xlarge's 256 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
Qwen3.6 27B	Alibaba	37.1#54	27B	—	65 GB
Qwen3.5 27B	Alibaba	33.8#77	27B	—	65 GB
Qwen3.6 35B A3B	Alibaba	31.6#96	35B	3B	84 GB
7 more models fit on p3dn.24xlarge 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 %
g6.48xlarge	US East (Virginia) (us-east-1)	192	768	L4	13.3504	-57%
g5.48xlarge	US East (Virginia) (us-east-1)	192	768	A10G	16.2880	-48%
p4d.24xlarge	US East (Virginia) (us-east-1)	96	1152	A100	21.9576	-30%
g6e.48xlarge	US East (Virginia) (us-east-1)	192	1536	L40S	30.1312	-3%