← All instances

g6e.12xlarge

⚡ 4x GPU • 192.0 GB

Part of the G6E Accelerated Computing family — Hardware accelerators (GPUs, FPGAs) for specialized compute.

Name:gGPU Graphics & ML Inferenceg = GPU Graphics & ML InferencePowered by GPUs (NVIDIA/AMD) for graphics-intensive applications, video encoding, remote workstations, and machine learning inference.66th Generation6 = 6th GenerationAWS 6th generation hardware platform with updated CPU/system architecture.eExtra Capacity / Expansione = Extra Capacity / ExpansionExpanded configuration offering a higher memory-to-vCPU ratio or increased local NVMe storage density per core.12xlarge12 Extra Large12xlarge = 12 Extra Large48 vCPUs • 384.0 GiB RAM • 3800 GB NVMe SSD • 100 Gigabit Network • 4x NVIDIA L40S (192.0 GB VRAM)
Price (Linux)
$10.4926/ hr
~$7,659.63/mo
Compute
48vCPUs
24 cores • x86_64
Memory
384.0GiB
8.0 GiB / vCPU
Value
$0.2186/ vCPU-hr
$0.0273/GiB-hr
Network
100Gbps
Baseline: 100 Gbps
Storage & EBS
2,500MB/s
Max: 80,000 IOPS

Technical Specifications & Limits

Hardware specs, container thresholds, and system limits

Compute & Processor

ProcessorAMD EPYC 7R13 Processor
Architecturex86_64 (x86_64)
vCPUs / Threads48 vCPUs
Physical Cores24
Clock Speed2.6 GHz
Intel AVX / AVX2No
Intel Turbo BoostNo
Bare MetalNo (Virtualized)

Performance & Benchmarks

CoreMark Score1,061,947
CoreMark / vCPU22,123.9 / core
FFmpeg Transcoding143 FPS
CoreMark per Dollar101,209 score / $
Cost per vCPU-hr$0.2186
Cost per GiB-hr$0.0273

Containers & Kubernetes

EKS Max Pods292 pods
Max ECS Tasks120 tasks
Max ENIs10
IPv4/v6 per ENI30
Total Addressable IPs300 total IPs
CNI Prefix DelegationSupported (High Density)

Networking & Bandwidth

Network Performance100 Gigabit
Baseline Bandwidth100 Gbps
Burst / Peak Bandwidth100 Gbps
Enhanced NetworkingYes
EFA SupportNo
IPv6 SupportNative Dual-Stack Supported

Storage & EBS Optimization

Storage ConfigurationNVMe SSD (3800 GB)
Local NVMe Disk3800 GB
EBS Baseline Throughput2500 MB/s
EBS Max Throughput2500 MB/s
EBS Baseline IOPS80,000
EBS Max / Burst IOPS80,000
Dedicated EBS Throughput20000 Mbps

GPU & Hardware Acceleration

GPU ModelNVIDIA L40S
Accelerator Count4x GPU(s)
Total GPU Memory192.0 GB
Memory ArchitectureGDDR / HBM
CUDA Compute Capabilityv8.9
Acceleration RuntimesCUDA, TensorRT, cuDNN, PyTorch, PyJAX

Platform & Architecture Details

Hypervisor / SystemAWS Nitro System (PCIe Offload)
Nitro EnclavesSupported (Isolated security enclaves)
Normalization Factor5.638170974
Generation StatusCurrent Generation (Recommended)
Date Introduced2024-08-15

Regional Pricing Matrix

Live on-demand rates across all global AWS cloud regions
Lowest Price Region
$10.4926/ hr
US East (N. Virginia) (us-east-1)
Highest Price Region
$15.2174/ hr
Asia Pacific (Tokyo) (ap-northeast-1)
Global Fleet Average
$12.3495/ hr
Across all active regions
Regional Coverage
12regions
Available worldwide
Linux — Available in all 12 regions
Region NameRegion CodeOn-Demand Price
Asia Pacific (Hyderabad)
ap-south-2$12.6013
Asia Pacific (Mumbai)
ap-south-1$12.6013
Asia Pacific (Osaka)Highest
ap-northeast-3$15.2174
Asia Pacific (Seoul)
ap-northeast-2$12.9001
Asia Pacific (Tokyo)Highest
ap-northeast-1$15.2174
EU (Frankfurt)
eu-central-1$13.1200
EU (Stockholm)
eu-north-1$11.1297
Europe (Spain)
eu-south-2$11.0564
Middle East (UAE)
me-central-1$12.8719
US East (N. Virginia)Lowest
us-east-1$10.4926
US East (Ohio)Lowest
us-east-2$10.4926
US West (Oregon)Lowest
us-west-2$10.4926