← All instances

g5.2xlarge

⚡ 1x GPU • 24.0 GB

Part of the G5 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.55th Generation5 = 5th GenerationAWS 5th 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 A10G (24.0 GB VRAM)
Price (Linux)
$1.2120/ hr
~$884.76/mo
Compute
8vCPUs
4 cores • x86_64
Memory
32.0GiB
4.0 GiB / vCPU
Value
$0.1515/ vCPU-hr
$0.0379/GiB-hr
Network
10Gbps
Baseline: 5 Gbps
Storage & EBS
437.5MB/s
Max: 15,000 IOPS

Technical Specifications & Limits

Hardware specs, container thresholds, and system limits

Compute & Processor

ProcessorAMD EPYC 7R32
Architecturex86_64 (x86_64)
vCPUs / Threads8 vCPUs
Physical Cores4
Clock Speed2.8 GHz
Intel AVX / AVX2No
Intel Turbo BoostNo
Bare MetalNo (Virtualized)

Performance & Benchmarks

CoreMark Score144,424
CoreMark / vCPU18,053 / core
FFmpeg Transcoding114 FPS
CoreMark per Dollar119,162 score / $
Cost per vCPU-hr$0.1515
Cost per GiB-hr$0.0379

Containers & Kubernetes

EKS Max Pods58 pods
Max ECS Tasks19 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 Throughput106.25 MB/s
EBS Max Throughput437.5 MB/s
EBS Baseline IOPS3,500
EBS Max / Burst IOPS15,000
Dedicated EBS ThroughputUp to 3500 Mbps

GPU & Hardware Acceleration

GPU ModelNVIDIA A10G
Accelerator Count1x GPU(s)
Total GPU Memory24.0 GB
Memory ArchitectureGDDR / HBM
CUDA Compute Capabilityv8.6
Acceleration RuntimesCUDA, TensorRT, cuDNN, PyTorch, PyJAX

Platform & Architecture Details

Hypervisor / SystemAWS Nitro System (PCIe Offload)
Nitro EnclavesSupported (Isolated security enclaves)
Normalization Factor1.204771372
Generation StatusCurrent Generation (Recommended)
Date Introduced2021-11-12

Regional Pricing Matrix

Live on-demand rates across all global AWS cloud regions
Lowest Price Region
$1.2120/ hr
US East (N. Virginia) (us-east-1)
Highest Price Region
$2.0602/ hr
South America (Sao Paulo) (sa-east-1)
Global Fleet Average
$1.4894/ hr
Across all active regions
Regional Coverage
19regions
Available worldwide
Linux — Available in all 19 regions
Region NameRegion CodeOn-Demand Price
Asia Pacific (Hong Kong)
ap-east-1$1.8659
Asia Pacific (Jakarta)
ap-southeast-3$1.6963
Asia Pacific (Mumbai)
ap-south-1$1.4554
Asia Pacific (Seoul)
ap-northeast-2$1.4903
Asia Pacific (Sydney)
ap-southeast-2$1.5758
Asia Pacific (Tokyo)
ap-northeast-1$1.7578
Canada (Central)
ca-central-1$1.3457
EU (Frankfurt)
eu-central-1$1.5156
EU (Ireland)
eu-west-1$1.3530
EU (London)
eu-west-2$1.5385
EU (Paris)
eu-west-3$1.5385
EU (Stockholm)
eu-north-1$1.2855
Europe (Spain)
eu-south-2$1.2771
Israel (Tel Aviv)
il-central-1$1.4206
Middle East (UAE)
me-central-1$1.4867
South America (Sao Paulo)Highest
sa-east-1$2.0602
US East (N. Virginia)Lowest
us-east-1$1.2120
US East (Ohio)Lowest
us-east-2$1.2120
US West (Oregon)Lowest
us-west-2$1.2120