← All instances

g7.48xlarge

⚡ 8x GPU • 256.0 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.48xlarge48 Extra Large48xlarge = 48 Extra Large192 vCPUs • 768.0 GiB RAM • 7600 GB NVMe SSD • 700 Gigabit Network • 8x NVIDIA RTX PRO 4500 Blackwell (256.0 GB VRAM)
Price (Linux)
$28.5133/ hr
~$20,814.69/mo
Compute
192vCPUs
192 cores • x86_64
Memory
768.0GiB
4.0 GiB / vCPU
Value
$0.1485/ vCPU-hr
$0.0371/GiB-hr
Network
350Gbps
Baseline: 350 Gbps
Storage & EBS
10,000MB/s
Max: 320,000 IOPS

Technical Specifications & Limits

Hardware specs, container thresholds, and system limits

Compute & Processor

ProcessorIntel Xeon Scalable (Granite Rapids)
Architecturex86_64 (x86_64)
vCPUs / Threads192 vCPUs
Physical Cores192
Clock Speed3.9 GHz
Intel AVX / AVX2AVX & AVX2 Supported
Intel Turbo BoostYes
Bare MetalNo (Virtualized)

Performance & Benchmarks

CoreMark Score5,701,982
CoreMark / vCPU29,697.8 / core
FFmpeg Transcoding301 FPS
CoreMark per Dollar199,976 score / $
Cost per vCPU-hr$0.1485
Cost per GiB-hr$0.0371

Containers & Kubernetes

EKS Max Pods758 pods
Max ECS Tasks—
Max ENIs24
IPv4/v6 per ENI64
Total Addressable IPs1536 total IPs
CNI Prefix DelegationSupported (High Density)

Networking & Bandwidth

Network Performance700 Gigabit
Baseline Bandwidth350 Gbps
Burst / Peak Bandwidth350 Gbps
Enhanced NetworkingYes
EFA SupportNo
IPv6 SupportNative Dual-Stack Supported

Storage & EBS Optimization

Storage ConfigurationNVMe SSD (7600 GB)
Local NVMe Disk7600 GB
EBS Baseline Throughput10000 MB/s
EBS Max Throughput10000 MB/s
EBS Baseline IOPS320,000
EBS Max / Burst IOPS320,000
Dedicated EBS Throughput80000 Mbps

GPU & Hardware Acceleration

GPU ModelNVIDIA RTX PRO 4500 Blackwell
Accelerator Count8x GPU(s)
Total GPU Memory256.0 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 Factor11.31479365
Generation StatusCurrent Generation (Recommended)
Date Introduced2026-06-18

Regional Pricing Matrix

Live on-demand rates across all global AWS cloud regions
Lowest Price Region
$28.5133/ hr
US East (N. Virginia) (us-east-1)
Highest Price Region
$29.9389/ hr
Europe (Spain) (eu-south-2)
Global Fleet Average
$28.8697/ 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$29.9389
US East (N. Virginia)Lowest
us-east-1$28.5133
US East (Ohio)Lowest
us-east-2$28.5133
US West (Oregon)Lowest
us-west-2$28.5133