g6e.4xlarge
⚡ 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.4xlarge4 Extra Large4xlarge = 4 Extra Large16 vCPUs • 128 GB RAM • 600 GB NVMe SSD • 20 Gbps Network • 1x NVIDIA L40S (48.0 GB VRAM)Price (Linux)
$3.0042/ hr
~$2,193.10/mo
Compute
16vCPUs
8 cores • x86_64
Memory
128GB
8.0 GB / vCPU
Value
$0.1878/ vCPU-hr
$0.0235/GB-hr
Network
20 Gbps
Baseline: 20 Gbps
Storage & EBS
1,000MB/s
Max: 32,000 IOPS
Technical Specifications & Limits
Hardware specs, container thresholds, and system limitsCompute & Processor
ProcessorAMD EPYC 7R13 Processor
Architecturex86_64 (x86_64)
vCPUs / Threads16 vCPUs
Physical Cores8
Clock Speed2.6 GHz
Intel AVX / AVX2No
Intel Turbo BoostNo
Bare MetalNo (Virtualized)
Performance & Benchmarks
CoreMark Score343,366
CoreMark / vCPU21,460.4 / core
FFmpeg Transcoding143 FPS
CoreMark per Dollar114,294 score / $
Cost per vCPU-hr$0.1878
Cost per GB-hr$0.0235
Containers & Kubernetes
EKS Max Pods234 pods
Max ECS Tasks60 tasks
Max ENIs8
IPv4/v6 per ENI30
Total Addressable IPs240 total IPs
CNI Prefix DelegationSupported (High Density)
Networking & Bandwidth
Network Performance20 Gbps
Baseline Bandwidth20 Gbps
Burst / Peak Bandwidth20 Gbps
Enhanced NetworkingYes
EFA SupportNo
IPv6 SupportNative Dual-Stack Supported
Storage & EBS Optimization
Storage ConfigurationNVMe SSD (600 GB)
Local NVMe Disk600 GB NVMe SSD
EBS Baseline Throughput1000 MB/s
EBS Max Throughput1000 MB/s
EBS Baseline IOPS32,000
EBS Max / Burst IOPS32,000
Dedicated EBS Throughput8000 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 Factor1.614314115
Generation StatusCurrent Generation (Recommended)
Date Introduced2024-08-15
Regional Pricing Matrix
Live on-demand rates across all global AWS cloud regionsLowest Price Region
$3.0042/ hr
US East (N. Virginia) (us-east-1)Highest Price Region
$4.3570/ hr
Asia Pacific (Tokyo) (ap-northeast-1)Global Fleet Average
$3.5359/ hr
Across all active regionsRegional Coverage
12regions
Available worldwide| Region | On-Demand Price |
|---|---|
ap-south-2 Asia Pacific (Hyderabad) | $3.6080 |
ap-south-1 Asia Pacific (Mumbai) | $3.6080 |
ap-northeast-3 HighestAsia Pacific (Osaka) | $4.3570 |
ap-northeast-2 Asia Pacific (Seoul) | $3.6936 |
ap-northeast-1 HighestAsia Pacific (Tokyo) | $4.3570 |
eu-central-1 EU (Frankfurt) | $3.7565 |
eu-north-1 EU (Stockholm) | $3.1867 |
eu-south-2 Europe (Spain) | $3.1657 |
me-central-1 Middle East (UAE) | $3.6855 |
us-east-1 LowestUS East (N. Virginia) | $3.0042 |
us-east-2 LowestUS East (Ohio) | $3.0042 |
us-west-2 LowestUS West (Oregon) | $3.0042 |
| Region | On-Demand Price |
|---|---|
ap-south-2 Asia Pacific (Hyderabad) | $4.3440 |
ap-south-1 Asia Pacific (Mumbai) | $4.3440 |
ap-northeast-3 HighestAsia Pacific (Osaka) | $5.0930 |
ap-northeast-2 Asia Pacific (Seoul) | $4.4295 |
ap-northeast-1 HighestAsia Pacific (Tokyo) | $5.0930 |
eu-central-1 EU (Frankfurt) | $4.4925 |
eu-north-1 EU (Stockholm) | $3.9227 |
eu-south-2 Europe (Spain) | $3.9017 |
me-central-1 Middle East (UAE) | $4.4215 |
us-east-1 LowestUS East (N. Virginia) | $3.7402 |
us-east-2 LowestUS East (Ohio) | $3.7402 |
us-west-2 LowestUS West (Oregon) | $3.7402 |
No regions matched your search filter.