← All instances

g6.2xlarge

⚡ 1x GPU • 24.0 GB

Part of the G6 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.2xlarge2 Extra Large2xlarge = 2 Extra Large8 vCPUs • 32.0 GiB RAM • 450 GB NVMe SSD • Up to 10 Gigabit Network • 1x NVIDIA L4 (24.0 GB VRAM)
Price (Linux)
$0.9776/ hr
~$713.65/mo
Compute
8vCPUs
4 cores • x86_64
Memory
32.0GiB
4.0 GiB / vCPU
Value
$0.1222/ vCPU-hr
$0.0306/GiB-hr
Network
10Gbps
Baseline: 5 Gbps
Storage & EBS
625MB/s
Max: 20,000 IOPS

Technical Specifications & Limits

Hardware specs, container thresholds, and system limits

Compute & Processor

ProcessorAMD EPYC 7R13 Processor
Architecturex86_64 (x86_64)
vCPUs / Threads8 vCPUs
Physical Cores4
Clock Speed2.6 GHz
Intel AVX / AVX2No
Intel Turbo BoostNo
Bare MetalNo (Virtualized)

Performance & Benchmarks

CoreMark Score167,347
CoreMark / vCPU20,918.3 / core
FFmpeg Transcoding133 FPS
CoreMark per Dollar171,181 score / $
Cost per vCPU-hr$0.1222
Cost per GiB-hr$0.0306

Containers & Kubernetes

EKS Max Pods58 pods
Max ECS Tasks40 tasks
Max ENIs4
IPv4/v6 per ENI15
Total Addressable IPs60 total IPs
CNI Prefix DelegationSupported (High Density)

Networking & Bandwidth

Network PerformanceUp to 10 Gigabit
Baseline Bandwidth5 Gbps
Burst / Peak Bandwidth10 Gbps
Enhanced NetworkingYes
EFA SupportNo
IPv6 SupportNative Dual-Stack Supported

Storage & EBS Optimization

Storage ConfigurationNVMe SSD (450 GB)
Local NVMe Disk450 GB
EBS Baseline Throughput250 MB/s
EBS Max Throughput625 MB/s
EBS Baseline IOPS8,000
EBS Max / Burst IOPS20,000
Dedicated EBS ThroughputUp to 5000 Mbps

GPU & Hardware Acceleration

GPU ModelNVIDIA L4
Accelerator Count1x GPU(s)
Total GPU Memory24.0 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 Factor1.21471173
Generation StatusCurrent Generation (Recommended)
Date Introduced2024-04-04

Regional Pricing Matrix

Live on-demand rates across all global AWS cloud regions
Lowest Price Region
$0.9776/ hr
US East (N. Virginia) (us-east-1)
Highest Price Region
$1.6617/ hr
South America (Sao Paulo) (sa-east-1)
Global Fleet Average
$1.1952/ hr
Across all active regions
Regional Coverage
20regions
Available worldwide
Linux — Available in all 20 regions
Region NameRegion CodeOn-Demand Price
Asia Pacific (Hyderabad)
ap-south-2$1.1739
Asia Pacific (Malaysia)
ap-southeast-5$1.2315
Asia Pacific (Mumbai)
ap-south-1$1.1739
Asia Pacific (Seoul)
ap-northeast-2$1.2021
Asia Pacific (Sydney)
ap-southeast-2$1.2711
Asia Pacific (Tokyo)
ap-northeast-1$1.4178
AWS GovCloud (US-East)
us-gov-east-1$1.2322
AWS GovCloud (US-West)
us-gov-west-1$1.2322
Canada (Central)
ca-central-1$1.0855
EU (Frankfurt)
eu-central-1$1.2225
EU (London)
eu-west-2$1.2409
EU (Paris)
eu-west-3$1.2409
EU (Stockholm)
eu-north-1$1.0369
Europe (Spain)
eu-south-2$1.0301
Europe (Zurich)
eu-central-2$1.3180
Middle East (UAE)
me-central-1$1.2004
South America (Sao Paulo)Highest
sa-east-1$1.6617
US East (N. Virginia)Lowest
us-east-1$0.9776
US East (Ohio)Lowest
us-east-2$0.9776
US West (Oregon)Lowest
us-west-2$0.9776