← All instances

g7.4xlarge

⚡ 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.4xlarge4 Extra Large4xlarge = 4 Extra Large16 vCPUs • 64.0 GiB RAM • 875 GB NVMe SSD • Up to 100 Gigabit Network • 1x NVIDIA RTX PRO 4500 Blackwell (32.0 GB VRAM)
Price (Linux)
$3.0421/ hr
~$2,220.72/mo
Compute
16vCPUs
16 cores • x86_64
Memory
64.0GiB
4.0 GiB / vCPU
Value
$0.1901/ vCPU-hr
$0.0475/GiB-hr
Network
100Gbps
Baseline: 80 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 / Threads16 vCPUs
Physical Cores16
Clock Speed3.9 GHz
Intel AVX / AVX2AVX & AVX2 Supported
Intel Turbo BoostYes
Bare MetalNo (Virtualized)

Performance & Benchmarks

CoreMark Score540,358
CoreMark / vCPU33,772.4 / core
FFmpeg Transcoding174 FPS
CoreMark per Dollar177,628 score / $
Cost per vCPU-hr$0.1901
Cost per GiB-hr$0.0475

Containers & Kubernetes

EKS Max Pods506 pods
Max ECS Tasks—
Max ENIs8
IPv4/v6 per ENI64
Total Addressable IPs512 total IPs
CNI Prefix DelegationSupported (High Density)

Networking & Bandwidth

Network PerformanceUp to 100 Gigabit
Baseline Bandwidth80 Gbps
Burst / Peak Bandwidth100 Gbps
Enhanced NetworkingYes
EFA SupportNo
IPv6 SupportNative Dual-Stack Supported

Storage & EBS Optimization

Storage ConfigurationNVMe SSD (875 GB)
Local NVMe Disk875 GB
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 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 Factor1.207174603
Generation StatusCurrent Generation (Recommended)
Date Introduced2026-06-18

Regional Pricing Matrix

Live on-demand rates across all global AWS cloud regions
Lowest Price Region
$3.0421/ hr
US East (N. Virginia) (us-east-1)
Highest Price Region
$3.1942/ hr
Europe (Spain) (eu-south-2)
Global Fleet Average
$3.0801/ 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$3.1942
US East (N. Virginia)Lowest
us-east-1$3.0421
US East (Ohio)Lowest
us-east-2$3.0421
US West (Oregon)Lowest
us-west-2$3.0421