← All instances

g6e.16xlarge

⚡ 1x GPU • 48.0 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.16xlarge16 Extra Large16xlarge = 16 Extra Large64 vCPUs • 512.0 GiB RAM • 1900 GB NVMe SSD • 35 Gigabit Network • 1x NVIDIA L40S (48.0 GB VRAM)
Price (Linux)
$7.5772/ hr
~$5,531.35/mo
Compute
64vCPUs
32 cores • x86_64
Memory
512.0GiB
8.0 GiB / vCPU
Value
$0.1184/ vCPU-hr
$0.0148/GiB-hr
Network
35Gbps
Baseline: 35 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 / Threads64 vCPUs
Physical Cores32
Clock Speed2.6 GHz
Intel AVX / AVX2No
Intel Turbo BoostNo
Bare MetalNo (Virtualized)

Performance & Benchmarks

CoreMark Score1,347,368
CoreMark / vCPU21,052.6 / core
FFmpeg Transcoding129 FPS
CoreMark per Dollar177,819 score / $
Cost per vCPU-hr$0.1184
Cost per GiB-hr$0.0148

Containers & Kubernetes

EKS Max Pods737 pods
Max ECS Tasks120 tasks
Max ENIs15
IPv4/v6 per ENI50
Total Addressable IPs750 total IPs
CNI Prefix DelegationSupported (High Density)

Networking & Bandwidth

Network Performance35 Gigabit
Baseline Bandwidth35 Gbps
Burst / Peak Bandwidth35 Gbps
Enhanced NetworkingYes
EFA SupportNo
IPv6 SupportNative Dual-Stack Supported

Storage & EBS Optimization

Storage ConfigurationNVMe SSD (1900 GB)
Local NVMe Disk1900 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 Count1x GPU(s)
Total GPU Memory48.0 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 Factor4.071570577
Generation StatusCurrent Generation (Recommended)
Date Introduced2024-08-15

Regional Pricing Matrix

Live on-demand rates across all global AWS cloud regions
Lowest Price Region
$7.5772/ hr
US East (N. Virginia) (us-east-1)
Highest Price Region
$10.9892/ hr
Asia Pacific (Tokyo) (ap-northeast-1)
Global Fleet Average
$8.9181/ 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$9.1000
Asia Pacific (Mumbai)
ap-south-1$9.1000
Asia Pacific (Osaka)Highest
ap-northeast-3$10.9892
Asia Pacific (Seoul)
ap-northeast-2$9.3157
Asia Pacific (Tokyo)Highest
ap-northeast-1$10.9892
EU (Frankfurt)
eu-central-1$9.4745
EU (Stockholm)
eu-north-1$8.0373
Europe (Spain)
eu-south-2$7.9844
Middle East (UAE)
me-central-1$9.2954
US East (N. Virginia)Lowest
us-east-1$7.5772
US East (Ohio)Lowest
us-east-2$7.5772
US West (Oregon)Lowest
us-west-2$7.5772