← All instances

g7.2xlarge

⚡ 1x GPU • 32.0 GB

Part of the G7 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.77th Generation7 = 7th GenerationAWS 7th generation hardware platform with updated CPU/system architecture.2xlarge2 Extra Large2xlarge = 2 Extra Large8 vCPUs • 32.0 GiB RAM • 440 GB NVMe SSD • Up to 60 Gigabit Network • 1x NVIDIA RTX PRO 4500 Blackwell (32.0 GB VRAM)
Price (Linux)
$2.5200/ hr
~$1,839.60/mo
Compute
8vCPUs
8 cores • x86_64
Memory
32.0GiB
4.0 GiB / vCPU
Value
$0.3150/ vCPU-hr
$0.0788/GiB-hr
Network
60Gbps
Baseline: 40 Gbps
Storage & EBS
1,000MB/s
Max: 32,000 IOPS

Technical Specifications & Limits

Hardware specs, container thresholds, and system limits

Compute & Processor

ProcessorIntel Xeon Scalable (Granite Rapids)
Architecturex86_64 (x86_64)
vCPUs / Threads8 vCPUs
Physical Cores8
Clock Speed3.9 GHz
Intel AVX / AVX2AVX & AVX2 Supported
Intel Turbo BoostYes
Bare MetalNo (Virtualized)

Performance & Benchmarks

CoreMark Score267,409
CoreMark / vCPU33,426.2 / core
FFmpeg Transcoding104 FPS
CoreMark per Dollar106,115 score / $
Cost per vCPU-hr$0.3150
Cost per GiB-hr$0.0788

Containers & Kubernetes

EKS Max Pods254 pods
Max ECS Tasks—
Max ENIs4
IPv4/v6 per ENI64
Total Addressable IPs256 total IPs
CNI Prefix DelegationSupported (High Density)

Networking & Bandwidth

Network PerformanceUp to 60 Gigabit
Baseline Bandwidth40 Gbps
Burst / Peak Bandwidth60 Gbps
Enhanced NetworkingYes
EFA SupportNo
IPv6 SupportNative Dual-Stack Supported

Storage & EBS Optimization

Storage ConfigurationNVMe SSD (440 GB)
Local NVMe Disk440 GB
EBS Baseline Throughput500 MB/s
EBS Max Throughput1000 MB/s
EBS Baseline IOPS16,000
EBS Max / Burst IOPS32,000
Dedicated EBS ThroughputUp to 8000 Mbps

GPU & Hardware Acceleration

GPU ModelNVIDIA RTX PRO 4500 Blackwell
Accelerator Count1x GPU(s)
Total GPU Memory32.0 GB
Memory ArchitectureGDDR / HBM
CUDA Compute Capabilityv12.0
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 Introduced2026-06-18

Regional Pricing Matrix

Live on-demand rates across all global AWS cloud regions
Lowest Price Region
$2.5200/ hr
US East (N. Virginia) (us-east-1)
Highest Price Region
$2.6460/ hr
Europe (Spain) (eu-south-2)
Global Fleet Average
$2.5515/ hr
Across all active regions
Regional Coverage
4regions
Available worldwide
Linux — Available in all 4 regions
Region NameRegion CodeOn-Demand Price
Europe (Spain)Highest
eu-south-2$2.6460
US East (N. Virginia)Lowest
us-east-1$2.5200
US East (Ohio)Lowest
us-east-2$2.5200
US West (Oregon)Lowest
us-west-2$2.5200