← All instances

g6.xlarge

⚡ 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.xlargeExtra Large (1x)xlarge = Extra Large (1x)4 vCPUs • 16.0 GiB RAM • 250 GB NVMe SSD • Up to 10 Gigabit Network • 1x NVIDIA L4 (24.0 GB VRAM)
Price (Linux)
$0.8048/ hr
~$587.50/mo
Compute
4vCPUs
2 cores • x86_64
Memory
16.0GiB
4.0 GiB / vCPU
Value
$0.2012/ vCPU-hr
$0.0503/GiB-hr
Network
10Gbps
Baseline: 2.5 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 / Threads4 vCPUs
Physical Cores2
Clock Speed2.6 GHz
Intel AVX / AVX2No
Intel Turbo BoostNo
Bare MetalNo (Virtualized)

Performance & Benchmarks

CoreMark Score83,814
CoreMark / vCPU20,953.4 / core
FFmpeg Transcoding134 FPS
CoreMark per Dollar104,143 score / $
Cost per vCPU-hr$0.2012
Cost per GiB-hr$0.0503

Containers & Kubernetes

EKS Max Pods58 pods
Max ECS Tasks20 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 Bandwidth2.5 Gbps
Burst / Peak Bandwidth10 Gbps
Enhanced NetworkingYes
EFA SupportNo
IPv6 SupportNative Dual-Stack Supported

Storage & EBS Optimization

Storage ConfigurationNVMe SSD (250 GB)
Local NVMe Disk250 GB
EBS Baseline Throughput125 MB/s
EBS Max Throughput625 MB/s
EBS Baseline IOPS4,000
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
Generation StatusCurrent Generation (Recommended)
Date Introduced2024-04-04

Regional Pricing Matrix

Live on-demand rates across all global AWS cloud regions
Lowest Price Region
$0.8048/ hr
US East (N. Virginia) (us-east-1)
Highest Price Region
$1.3680/ hr
South America (Sao Paulo) (sa-east-1)
Global Fleet Average
$0.9840/ 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$0.9664
Asia Pacific (Malaysia)
ap-southeast-5$1.0138
Asia Pacific (Mumbai)
ap-south-1$0.9664
Asia Pacific (Seoul)
ap-northeast-2$0.9896
Asia Pacific (Sydney)
ap-southeast-2$1.0464
Asia Pacific (Tokyo)
ap-northeast-1$1.1672
AWS GovCloud (US-East)
us-gov-east-1$1.0144
AWS GovCloud (US-West)
us-gov-west-1$1.0144
Canada (Central)
ca-central-1$0.8936
EU (Frankfurt)
eu-central-1$1.0064
EU (London)
eu-west-2$1.0216
EU (Paris)
eu-west-3$1.0216
EU (Stockholm)
eu-north-1$0.8536
Europe (Spain)
eu-south-2$0.8480
Europe (Zurich)
eu-central-2$1.0850
Middle East (UAE)
me-central-1$0.9882
South America (Sao Paulo)Highest
sa-east-1$1.3680
US East (N. Virginia)Lowest
us-east-1$0.8048
US East (Ohio)Lowest
us-east-2$0.8048
US West (Oregon)Lowest
us-west-2$0.8048