← All instances

g5g.16xlarge

⚡ 2x GPU • 32.0 GB

Part of the G5G 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.gAWS Gravitong = AWS GravitonAWS Graviton2 Processor (arm64). Powered by custom 64-bit ARM AWS Graviton processors, delivering industry-leading price-performance and power efficiency.16xlarge16 Extra Large16xlarge = 16 Extra Large64 vCPUs • 128.0 GiB RAM • EBS only • 25 Gigabit Network • 2x NVIDIA T4G Tensor Core (32.0 GB VRAM)
Price (Linux)
$2.7440/ hr
~$2,003.12/mo
Compute
64vCPUs
64 cores • arm64
Memory
128.0GiB
2.0 GiB / vCPU
Value
$0.0429/ vCPU-hr
$0.0214/GiB-hr
Network
25Gbps
Baseline: 25 Gbps
Storage & EBS
2,375MB/s
Max: 80,000 IOPS

Technical Specifications & Limits

Hardware specs, container thresholds, and system limits

Compute & Processor

ProcessorAWS Graviton2 Processor
Architecturearm64 (ARM64 (Graviton))
vCPUs / Threads64 vCPUs
Physical Cores64
Clock Speed2.5 GHz
Intel AVX / AVX2No
Intel Turbo BoostNo
Bare MetalNo (Virtualized)

Performance & Benchmarks

CoreMark Score1,283,422
CoreMark / vCPU20,053.5 / core
FFmpeg Transcoding100 FPS
CoreMark per Dollar467,719 score / $
Cost per vCPU-hr$0.0429
Cost per GiB-hr$0.0214

Containers & Kubernetes

EKS Max Pods737 pods
Max ECS Tasks120 tasks
Max ENIs15
IPv4/v6 per ENI50
Total Addressable IPs750 total IPs
CNI Prefix DelegationSupported (High Density)

Networking & Bandwidth

Network Performance25 Gigabit
Baseline Bandwidth25 Gbps
Burst / Peak Bandwidth25 Gbps
Enhanced NetworkingYes
EFA SupportNo
IPv6 SupportNative Dual-Stack Supported

Storage & EBS Optimization

Storage ConfigurationEBS only
Local NVMe DiskNone (EBS only)
EBS Baseline Throughput2375 MB/s
EBS Max Throughput2375 MB/s
EBS Baseline IOPS80,000
EBS Max / Burst IOPS80,000
Dedicated EBS Throughput19000 Mbps

GPU & Hardware Acceleration

GPU ModelNVIDIA T4G Tensor Core
Accelerator Count2x GPU(s)
Total GPU Memory32.0 GB
Memory ArchitectureGDDR / HBM
CUDA Compute Capabilityv7.5
Acceleration RuntimesCUDA, TensorRT, cuDNN, PyTorch, PyJAX

Platform & Architecture Details

Hypervisor / SystemAWS Nitro System (PCIe Offload)
Nitro EnclavesNot Supported
Normalization Factor6.533333333
Generation StatusCurrent Generation (Recommended)
Date Introduced2021-11-29

Regional Pricing Matrix

Live on-demand rates across all global AWS cloud regions
Lowest Price Region
$2.7440/ hr
US East (N. Virginia) (us-east-1)
Highest Price Region
$3.8395/ hr
Asia Pacific (Singapore) (ap-southeast-1)
Global Fleet Average
$3.2716/ hr
Across all active regions
Regional Coverage
7regions
Available worldwide
Linux — Available in all 7 regions
Region NameRegion CodeOn-Demand Price
Asia Pacific (Seoul)
ap-northeast-2$3.3752
Asia Pacific (Singapore)Highest
ap-southeast-1$3.8395
Asia Pacific (Tokyo)
ap-northeast-1$3.7039
EU (Frankfurt)
eu-central-1$3.4326
Europe (Spain)
eu-south-2$3.0622
US East (N. Virginia)Lowest
us-east-1$2.7440
US West (Oregon)Lowest
us-west-2$2.7440