← All instances

g4ad.16xlarge

⚡ 4x GPU • 32.0 GB

Part of the G4AD 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.44th Generation4 = 4th GenerationAWS 4th generation hardware platform with updated CPU/system architecture.aAMD EPYCa = AMD EPYCAMD EPYC 7R32 (x86_64). Powered by AMD EPYC x86_64 processors, delivering high core counts and cost-effective compute performance.dDirect-Attached NVMe SSDd = Direct-Attached NVMe SSDEquipped with physical high-speed NVMe SSD instance store volumes attached locally to the host server for temporary scratch and caching.16xlarge16 Extra Large16xlarge = 16 Extra Large64 vCPUs • 256.0 GiB RAM • 2400 GB NVMe SSD • 25 Gigabit Network • 4x AMD Radeon Pro V520 (32.0 GB VRAM)
Price (Linux)
$3.4680/ hr
~$2,531.64/mo
Compute
64vCPUs
32 cores • x86_64
Memory
256.0GiB
4.0 GiB / vCPU
Value
$0.0542/ vCPU-hr
$0.0135/GiB-hr
Network
25Gbps
Baseline: 25 Gbps
Storage & EBS
787.5MB/s
Max: 26,667 IOPS

Technical Specifications & Limits

Hardware specs, container thresholds, and system limits

Compute & Processor

ProcessorAMD EPYC 7R32
Architecturex86_64 (x86_64)
vCPUs / Threads64 vCPUs
Physical Cores32
Clock Speed2.8 GHz
Intel AVX / AVX2No
Intel Turbo BoostNo
Bare MetalNo (Virtualized)

Performance & Benchmarks

CoreMark Score1,251,100
CoreMark / vCPU19,548.4 / core
FFmpeg Transcoding175 FPS
CoreMark per Dollar360,755 score / $
Cost per vCPU-hr$0.0542
Cost per GiB-hr$0.0135

Containers & Kubernetes

EKS Max Pods234 pods
Max ECS Tasks12 tasks
Max ENIs8
IPv4/v6 per ENI30
Total Addressable IPs240 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 ConfigurationNVMe SSD (2400 GB)
Local NVMe Disk2400 GB
EBS Baseline Throughput787.5 MB/s
EBS Max Throughput787.5 MB/s
EBS Baseline IOPS26,667
EBS Max / Burst IOPS26,667
Dedicated EBS Throughput6000 Mbps

GPU & Hardware Acceleration

GPU ModelAMD Radeon Pro V520
Accelerator Count4x GPU(s)
Total GPU Memory32.0 GB
Memory ArchitectureGDDR / HBM
CUDA Compute Capability—
Acceleration RuntimesCUDA, TensorRT, cuDNN, PyTorch, PyJAX

Platform & Architecture Details

Hypervisor / SystemAWS Nitro System (PCIe Offload)
Nitro EnclavesNot Supported
Normalization Factor128
Generation StatusCurrent Generation (Recommended)
Date Introduced2020-12-09

Regional Pricing Matrix

Live on-demand rates across all global AWS cloud regions
Lowest Price Region
$3.4680/ hr
US East (N. Virginia) (us-east-1)
Highest Price Region
$4.6800/ hr
Asia Pacific (Tokyo) (ap-northeast-1)
Global Fleet Average
$3.9025/ hr
Across all active regions
Regional Coverage
8regions
Available worldwide
Linux — Available in all 8 regions
Region NameRegion CodeOn-Demand Price
Asia Pacific (Tokyo)Highest
ap-northeast-1$4.6800
Canada (Central)
ca-central-1$3.8720
EU (Frankfurt)
eu-central-1$4.3360
EU (Ireland)
eu-west-1$3.8720
EU (London)
eu-west-2$4.0560
US East (N. Virginia)Lowest
us-east-1$3.4680
US East (Ohio)Lowest
us-east-2$3.4680
US West (Oregon)Lowest
us-west-2$3.4680