g2.8xlarge
⚡ 4x GPUPrev GenPart of the G2 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.22nd Generation2 = 2nd GenerationAWS 2nd generation hardware platform with updated CPU/system architecture.8xlarge8 Extra Large8xlarge = 8 Extra Large32 vCPUs • 60.0 GiB RAM • 240 GB SSD • High Network • 4x NVIDIA GRID K520Price (Linux)
$2.6000/ hr
~$1,898.00/mo
Compute
32vCPUs
32 threads • x86_64
Memory
60.0GiB
1.9 GiB / vCPU
Value
$0.0813/ vCPU-hr
$0.0433/GiB-hr
Network
High
High
Storage & EBS
240 GB
240 GB
Technical Specifications & Limits
Hardware specs, container thresholds, and system limitsCompute & Processor
ProcessorIntel Xeon E5-2670 (Sandy Bridge)
Architecturex86_64 (x86_64)
vCPUs / Threads32 vCPUs
Physical Cores—
Clock Speed2.6 GHz
Intel AVX / AVX2AVX Supported
Intel Turbo BoostYes
Bare MetalNo (Virtualized)
Performance & Benchmarks
CoreMark ScoreNot benchmarked
CoreMark / vCPU—
FFmpeg Transcoding—
CoreMark per Dollar—
Cost per vCPU-hr$0.0813
Cost per GiB-hr$0.0433
Containers & Kubernetes
EKS Max Pods—
Max ECS Tasks—
Max ENIs—
IPv4/v6 per ENI—
Total Addressable IPs—
CNI Prefix DelegationStandard CNI
Networking & Bandwidth
Network PerformanceHigh
Baseline Bandwidth—
Burst / Peak Bandwidth—
Enhanced NetworkingNo
EFA SupportNo
IPv6 SupportNative Dual-Stack Supported
Storage & EBS Optimization
Storage ConfigurationSSD (240 GB)
Local NVMe Disk240 GB
EBS Baseline Throughput—
EBS Max Throughput—
EBS Baseline IOPS—
EBS Max / Burst IOPS—
Dedicated EBS Throughput1 Mbps
GPU & Hardware Acceleration
GPU ModelNVIDIA GRID K520
Accelerator Count4x GPU(s)
Total GPU Memory—
Memory ArchitectureGDDR / HBM
CUDA Compute Capabilityv3.0
Acceleration RuntimesCUDA, TensorRT, cuDNN, PyTorch, PyJAX
Platform & Architecture Details
Hypervisor / SystemXen Hypervisor
Nitro EnclavesNot Supported
Normalization Factor64
Generation StatusPrevious Generation
Date Introduced2015-04-16
Regional Pricing Matrix
Live on-demand rates across all global AWS cloud regionsLowest Price Region
$2.6000/ hr
US East (N. Virginia) (us-east-1)Highest Price Region
$4.0000/ hr
Asia Pacific (Singapore) (ap-southeast-1)Global Fleet Average
$3.1867/ hr
Across all active regionsRegional Coverage
9regions
Available worldwide| Region Name | Region Code | On-Demand Price |
|---|---|---|
Asia Pacific (Seoul) | ap-northeast-2 | $3.5920 |
Asia Pacific (Singapore)Highest | ap-southeast-1 | $4.0000 |
Asia Pacific (Sydney) | ap-southeast-2 | $3.5920 |
Asia Pacific (Tokyo) | ap-northeast-1 | $3.5920 |
EU (Frankfurt) | eu-central-1 | $3.0880 |
EU (Ireland) | eu-west-1 | $2.8080 |
US East (N. Virginia)Lowest | us-east-1 | $2.6000 |
US West (N. California) | us-west-1 | $2.8080 |
US West (Oregon)Lowest | us-west-2 | $2.6000 |
| Region Name | Region Code | On-Demand Price |
|---|---|---|
Asia Pacific (Seoul)Highest | ap-northeast-2 | $5.0640 |
Asia Pacific (Singapore) | ap-southeast-1 | $4.2780 |
Asia Pacific (Sydney) | ap-southeast-2 | $3.8700 |
Asia Pacific (Tokyo) | ap-northeast-1 | $3.8700 |
EU (Frankfurt) | eu-central-1 | $3.3660 |
EU (Ireland) | eu-west-1 | $3.0860 |
US East (N. Virginia)Lowest | us-east-1 | $2.8780 |
US West (N. California) | us-west-1 | $3.0860 |
US West (Oregon)Lowest | us-west-2 | $2.8780 |
No regions matched your search filter.