AWS Amazon EC2
g3.16xlarge
⚡ 4x GPU • 32 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 GB RAM • EBS only • 20 Gbps Network • 4x GPU (32.0 GB VRAM)On-demand, Linux
$4.5600/ hr
~$3,328.80/mo · lowest in US East (N. Virginia), us-east-1Per unit
$0.0712/ vCPU-hr
$0.0093/GB-hrCompute
64vCPUs
64 threads • x86_64Memory
488GB
7.6 GB / vCPUNetwork
20 Gbps
StandardStorage & EBS
EBSOnly
EBS onlyOn Google Cloud
g3.16xlarge is an accelerated machine. Those are compared by the accelerator, not by vCPU and memory, so this page doesn't pick a match. Browse Google Cloud machines.
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 Metal—
Performance & Benchmarks
CoreMark ScoreNot benchmarked
CoreMark / vCPU—
FFmpeg Transcoding—
CoreMark per Dollar—
Cost per vCPU-hr$0.0712
Cost per GB-hr$0.0093
Containers & Kubernetes
EKS Max Pods—
Max ENIs—
IPv4/v6 per ENI—
Total Addressable IPs—
CNI Prefix Delegation—
Networking & Bandwidth
Network Performance20 Gbps
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 Model—
Accelerator Count4x GPU(s)
Total GPU Memory32.0 GB
Memory Architecture—
Acceleration Runtimes—
Platform & Architecture Details
Hypervisor / System—
Nitro Enclaves—
Normalization Factor128
Generation StatusCurrent Generation (Recommended)
Rates by region
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 | On-Demand Price | % vs On-Demand Rate |
|---|---|---|
ap-northeast-2 Asia Pacific (Seoul) | $5.6800 | |
ap-southeast-1 Asia Pacific (Singapore) | $6.6800 | |
ap-southeast-2 HighestAsia Pacific (Sydney) | $7.0160 | |
ap-northeast-1 Asia Pacific (Tokyo) | $6.3200 | |
us-gov-west-1 AWS GovCloud (US-West) | $5.2800 | |
ca-central-1 Canada (Central) | $5.6640 | |
eu-central-1 EU (Frankfurt) | $5.7000 | |
eu-west-1 EU (Ireland) | $4.8400 | |
eu-west-2 EU (London) | $5.7160 | |
us-east-1 LowestUS East (N. Virginia) | $4.5600 | |
us-east-2 LowestUS East (Ohio) | $4.5600 | |
us-west-1 US West (N. California) | $6.1360 | |
us-west-2 LowestUS West (Oregon) | $4.5600 |
| Region | On-Demand Price | % vs On-Demand Rate |
|---|---|---|
ap-northeast-2 Asia Pacific (Seoul) | $8.6240 | |
ap-southeast-1 Asia Pacific (Singapore) | $9.6240 | |
ap-southeast-2 HighestAsia Pacific (Sydney) | $9.9600 | |
ap-northeast-1 Asia Pacific (Tokyo) | $9.2640 | |
us-gov-west-1 AWS GovCloud (US-West) | $8.2240 | |
ca-central-1 Canada (Central) | $8.6080 | |
eu-central-1 EU (Frankfurt) | $8.6440 | |
eu-west-1 EU (Ireland) | $7.7840 | |
eu-west-2 EU (London) | $8.6600 | |
us-east-1 LowestUS East (N. Virginia) | $7.5040 | |
us-east-2 LowestUS East (Ohio) | $7.5040 | |
us-west-1 US West (N. California) | $9.0800 | |
us-west-2 LowestUS West (Oregon) | $7.5040 |
No regions matched your search filter.