g4dn.16xlarge
⚡ 1x GPU • 16 GBPart of the G4DN 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.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.nEnhanced Networkingn = Enhanced NetworkingEnhanced networking capabilities delivering up to 100/200/400 Gbps network bandwidth and Elastic Fabric Adapter (EFA) support.16xlarge16 Extra Large16xlarge = 16 Extra Large64 vCPUs • 256 GB RAM • 900 GB NVMe SSD • 50 Gbps Network • 1x NVIDIA T4 Tensor Core (16.0 GB VRAM)Price (Linux)
$4.3520/ hr
~$3,176.96/mo
Compute
64vCPUs
32 cores • x86_64
Memory
256GB
4.0 GB / vCPU
Value
$0.0680/ vCPU-hr
$0.0170/GB-hr
Network
50 Gbps
Baseline: 50 Gbps
Storage & EBS
1,187.5MB/s
Max: 40,000 IOPS
Alternatives to g4dn.16xlarge
| Option | Price vs g4dn.16xlarge | Why look at it |
|---|---|---|
| g5.16xlargeCompare → | -6%-$0.256/hr Linux on-demand, us-east-1 | AMD (x86_64), newer generation, same vCPU and RAM |
| g6.16xlargeCompare → | -22%-$0.955/hr Linux on-demand, us-east-1 | AMD (x86_64), newer generation, same vCPU and RAM |
Technical Specifications & Limits
Hardware specs, container thresholds, and system limitsCompute & Processor
ProcessorIntel Xeon Family
Architecturex86_64 (x86_64)
vCPUs / Threads64 vCPUs
Physical Cores32
Clock Speed2.5 GHz
Intel AVX / AVX2AVX & AVX2 Supported
Intel Turbo BoostYes
Bare MetalNo (Virtualized)
Performance & Benchmarks
CoreMark Score914,808
CoreMark / vCPU14,293.9 / core
FFmpeg Transcoding105 FPS
CoreMark per Dollar210,204 score / $
Cost per vCPU-hr$0.0680
Cost per GB-hr$0.0170
Containers & Kubernetes
EKS Max Pods58 pods
Max ECS Tasks120 tasks
Max ENIs4
IPv4/v6 per ENI15
Total Addressable IPs60 total IPs
CNI Prefix DelegationSupported (High Density)
Networking & Bandwidth
Network Performance50 Gbps
Baseline Bandwidth50 Gbps
Burst / Peak Bandwidth50 Gbps
Enhanced NetworkingYes
EFA SupportNo
IPv6 SupportNative Dual-Stack Supported
Storage & EBS Optimization
Storage ConfigurationNVMe SSD (900 GB)
Local NVMe Disk900 GB NVMe SSD
EBS Baseline Throughput1187.5 MB/s
EBS Max Throughput1187.5 MB/s
EBS Baseline IOPS40,000
EBS Max / Burst IOPS40,000
Dedicated EBS Throughput7000 Mbps
GPU & Hardware Acceleration
GPU ModelNVIDIA T4 Tensor Core
Accelerator Count1x GPU(s)
Total GPU Memory16.0 GB
Memory ArchitectureGDDR / HBM
CUDA Compute Capabilityv7.5
Acceleration RuntimesCUDA, TensorRT, cuDNN, PyTorch, PyJAX
Platform & Architecture Details
Hypervisor / SystemAWS Nitro System (PCIe Offload)
Nitro EnclavesSupported (Isolated security enclaves)
Normalization Factor8.273764259
Generation StatusCurrent Generation (Recommended)
Date Introduced2019-09-20
Regional Pricing Matrix
Live on-demand rates across all global AWS cloud regionsLowest Price Region
$4.3520/ hr
US East (N. Virginia) (us-east-1)Highest Price Region
$7.3970/ hr
South America (Sao Paulo) (sa-east-1)Global Fleet Average
$5.3476/ hr
Across all active regionsRegional Coverage
24regions
Available worldwide| Region | On-Demand Price |
|---|---|
af-south-1 Africa (Cape Town) | $5.7740 |
ap-east-1 Asia Pacific (Hong Kong) | $6.7020 |
ap-south-1 Asia Pacific (Mumbai) | $4.7910 |
ap-northeast-3 Asia Pacific (Osaka) | $5.8750 |
ap-northeast-2 Asia Pacific (Seoul) | $5.3530 |
ap-southeast-1 Asia Pacific (Singapore) | $6.0890 |
ap-southeast-2 Asia Pacific (Sydney) | $5.6590 |
ap-northeast-1 Asia Pacific (Tokyo) | $5.8750 |
us-gov-east-1 AWS GovCloud (US-East) | $5.4860 |
us-gov-west-1 AWS GovCloud (US-West) | $5.4860 |
ca-central-1 Canada (Central) | $4.8320 |
eu-central-1 EU (Frankfurt) | $5.4400 |
eu-west-1 EU (Ireland) | $4.8530 |
eu-west-2 EU (London) | $5.0920 |
eu-south-1 EU (Milan) | $5.0950 |
eu-west-3 EU (Paris) | $5.0880 |
eu-north-1 EU (Stockholm) | $4.6170 |
me-south-1 Middle East (Bahrain) | $5.3380 |
sa-east-1 HighestSouth America (Sao Paulo) | $7.3970 |
us-east-1 LowestUS East (N. Virginia) | $4.3520 |
us-east-2 LowestUS East (Ohio) | $4.3520 |
us-west-2-lax-1 US West (Los Angeles) | $5.2220 |
us-west-1 US West (N. California) | $5.2220 |
us-west-2 LowestUS West (Oregon) | $4.3520 |
| Region | On-Demand Price |
|---|---|
af-south-1 Africa (Cape Town) | $8.7180 |
ap-east-1 Asia Pacific (Hong Kong) | $9.6460 |
ap-south-1 Asia Pacific (Mumbai) | $7.7350 |
ap-northeast-3 Asia Pacific (Osaka) | $8.8190 |
ap-northeast-2 Asia Pacific (Seoul) | $8.2970 |
ap-southeast-1 Asia Pacific (Singapore) | $9.0330 |
ap-southeast-2 Asia Pacific (Sydney) | $8.6030 |
ap-northeast-1 Asia Pacific (Tokyo) | $8.8190 |
us-gov-east-1 AWS GovCloud (US-East) | $8.4300 |
us-gov-west-1 AWS GovCloud (US-West) | $8.4300 |
ca-central-1 Canada (Central) | $7.7760 |
eu-central-1 EU (Frankfurt) | $8.3840 |
eu-west-1 EU (Ireland) | $7.7970 |
eu-west-2 EU (London) | $8.0360 |
eu-south-1 EU (Milan) | $8.0390 |
eu-west-3 EU (Paris) | $8.0320 |
eu-north-1 EU (Stockholm) | $7.5610 |
me-south-1 Middle East (Bahrain) | $8.2820 |
sa-east-1 HighestSouth America (Sao Paulo) | $10.3410 |
us-east-1 LowestUS East (N. Virginia) | $7.2960 |
us-east-2 LowestUS East (Ohio) | $7.2960 |
us-west-2-lax-1 US West (Los Angeles) | $8.1660 |
us-west-1 US West (N. California) | $8.1660 |
us-west-2 LowestUS West (Oregon) | $7.2960 |
No regions matched your search filter.