g3.16xlarge
⚡ 4x GPU • 32.0 GBPart of the G3 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.33rd Generation3 = 3rd GenerationAWS 3rd generation hardware platform with updated CPU/system architecture.16xlarge16 Extra Large16xlarge = 16 Extra Large64 vCPUs • 488.0 GiB RAM • EBS only • 20 Gigabit Network • 4x NVIDIA Tesla M60 (32.0 GB VRAM)Price (Linux)
$4.5600/ hr
~$3,328.80/mo
Compute
64vCPUs
64 threads • x86_64
Memory
488.0GiB
7.6 GiB / vCPU
Value
$0.0712/ vCPU-hr
$0.0093/GiB-hr
Network
20 Gigabit
20 Gigabit
Storage & EBS
EBSOnly
EBS-optimized
Technical Specifications & Limits
Hardware specs, container thresholds, and system limitsCompute & Processor
ProcessorIntel Xeon E5-2686 v4 (Broadwell)
Architecturex86_64 (x86_64)
vCPUs / Threads64 vCPUs
Physical Cores—
Clock Speed2.3 GHz
Intel AVX / AVX2AVX & AVX2 Supported
Intel Turbo BoostYes
Bare MetalNo (Virtualized)
Performance & Benchmarks
CoreMark ScoreNot benchmarked
CoreMark / vCPU—
FFmpeg Transcoding—
CoreMark per Dollar—
Cost per vCPU-hr$0.0712
Cost per GiB-hr$0.0093
Containers & Kubernetes
EKS Max Pods—
Max ECS Tasks—
Max ENIs—
IPv4/v6 per ENI—
Total Addressable IPs—
CNI Prefix DelegationStandard CNI
Networking & Bandwidth
Network Performance20 Gigabit
Baseline Bandwidth—
Burst / Peak Bandwidth—
Enhanced NetworkingYes
EFA SupportNo
IPv6 SupportNative Dual-Stack Supported
Storage & EBS Optimization
Storage ConfigurationEBS only
Local NVMe DiskNone (EBS only)
EBS Baseline Throughput—
EBS Max Throughput—
EBS Baseline IOPS—
EBS Max / Burst IOPS—
Dedicated EBS Throughput14000 Mbps
GPU & Hardware Acceleration
GPU ModelNVIDIA Tesla M60
Accelerator Count4x GPU(s)
Total GPU Memory32.0 GB
Memory ArchitectureGDDR / HBM
CUDA Compute Capabilityv5.2
Acceleration RuntimesCUDA, TensorRT, cuDNN, PyTorch, PyJAX
Platform & Architecture Details
Hypervisor / SystemXen Hypervisor
Nitro EnclavesNot Supported
Normalization Factor128
Generation StatusCurrent Generation (Recommended)
Date Introduced2017-07-13
Regional Pricing Matrix
Live on-demand rates across all global AWS cloud regionsLowest Price Region
$4.5600/ hr
US East (N. Virginia) (us-east-1)Highest Price Region
$7.0160/ hr
Asia Pacific (Sydney) (ap-southeast-2)Global Fleet Average
$5.5932/ hr
Across all active regionsRegional Coverage
13regions
Available worldwide| Region Name | Region Code | On-Demand Price |
|---|---|---|
Asia Pacific (Seoul) | ap-northeast-2 | $5.6800 |
Asia Pacific (Singapore) | ap-southeast-1 | $6.6800 |
Asia Pacific (Sydney)Highest | ap-southeast-2 | $7.0160 |
Asia Pacific (Tokyo) | ap-northeast-1 | $6.3200 |
AWS GovCloud (US-West) | us-gov-west-1 | $5.2800 |
Canada (Central) | ca-central-1 | $5.6640 |
EU (Frankfurt) | eu-central-1 | $5.7000 |
EU (Ireland) | eu-west-1 | $4.8400 |
EU (London) | eu-west-2 | $5.7160 |
US East (N. Virginia)Lowest | us-east-1 | $4.5600 |
US East (Ohio)Lowest | us-east-2 | $4.5600 |
US West (N. California) | us-west-1 | $6.1360 |
US West (Oregon)Lowest | us-west-2 | $4.5600 |
| Region Name | Region Code | On-Demand Price |
|---|---|---|
Asia Pacific (Seoul) | ap-northeast-2 | $8.6240 |
Asia Pacific (Singapore) | ap-southeast-1 | $9.6240 |
Asia Pacific (Sydney)Highest | ap-southeast-2 | $9.9600 |
Asia Pacific (Tokyo) | ap-northeast-1 | $9.2640 |
AWS GovCloud (US-West) | us-gov-west-1 | $8.2240 |
Canada (Central) | ca-central-1 | $8.6080 |
EU (Frankfurt) | eu-central-1 | $8.6440 |
EU (Ireland) | eu-west-1 | $7.7840 |
EU (London) | eu-west-2 | $8.6600 |
US East (N. Virginia)Lowest | us-east-1 | $7.5040 |
US East (Ohio)Lowest | us-east-2 | $7.5040 |
US West (N. California) | us-west-1 | $9.0800 |
US West (Oregon)Lowest | us-west-2 | $7.5040 |
No regions matched your search filter.