g6e.16xlarge
⚡ 1x GPU • 48 GBPart 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 GB RAM • 1900 GB NVMe SSD • 35 Gbps Network • 1x NVIDIA L40S (48.0 GB VRAM)Price (Linux)
$7.5772/ hr
~$5,531.35/mo
Compute
64vCPUs
32 cores • x86_64
Memory
512GB
8.0 GB / vCPU
Value
$0.1184/ vCPU-hr
$0.0148/GB-hr
Network
35 Gbps
Baseline: 35 Gbps
Storage & EBS
2,500MB/s
Max: 80,000 IOPS
Technical Specifications & Limits
Hardware specs, container thresholds, and system limitsCompute & 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 GB-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 Gbps
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 Disk1,900 GB NVMe SSD
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 regionsLowest 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 regionsRegional Coverage
12regions
Available worldwide| Region | On-Demand Price |
|---|---|
ap-south-2 Asia Pacific (Hyderabad) | $9.1000 |
ap-south-1 Asia Pacific (Mumbai) | $9.1000 |
ap-northeast-3 HighestAsia Pacific (Osaka) | $10.9892 |
ap-northeast-2 Asia Pacific (Seoul) | $9.3157 |
ap-northeast-1 HighestAsia Pacific (Tokyo) | $10.9892 |
eu-central-1 EU (Frankfurt) | $9.4745 |
eu-north-1 EU (Stockholm) | $8.0373 |
eu-south-2 Europe (Spain) | $7.9844 |
me-central-1 Middle East (UAE) | $9.2954 |
us-east-1 LowestUS East (N. Virginia) | $7.5772 |
us-east-2 LowestUS East (Ohio) | $7.5772 |
us-west-2 LowestUS West (Oregon) | $7.5772 |
| Region | On-Demand Price |
|---|---|
ap-south-2 Asia Pacific (Hyderabad) | $12.0440 |
ap-south-1 Asia Pacific (Mumbai) | $12.0440 |
ap-northeast-3 HighestAsia Pacific (Osaka) | $13.9332 |
ap-northeast-2 Asia Pacific (Seoul) | $12.2598 |
ap-northeast-1 HighestAsia Pacific (Tokyo) | $13.9332 |
eu-central-1 EU (Frankfurt) | $12.4185 |
eu-north-1 EU (Stockholm) | $10.9813 |
eu-south-2 Europe (Spain) | $10.9284 |
me-central-1 Middle East (UAE) | $12.2394 |
us-east-1 LowestUS East (N. Virginia) | $10.5212 |
us-east-2 LowestUS East (Ohio) | $10.5212 |
us-west-2 LowestUS West (Oregon) | $10.5212 |
No regions matched your search filter.