← All instances

g6.48xlarge

⚡ 8x GPU • 192.0 GB

Part of the G6 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.66th Generation6 = 6th GenerationAWS 6th generation hardware platform with updated CPU/system architecture.48xlarge48 Extra Large48xlarge = 48 Extra Large192 vCPUs • 768.0 GiB RAM • 7520 GB NVMe SSD • 100 Gigabit Network • 8x NVIDIA L4 (192.0 GB VRAM)
Price (Linux)
$13.3504/ hr
~$9,745.79/mo
Compute
192vCPUs
96 cores • x86_64
Memory
768.0GiB
4.0 GiB / vCPU
Value
$0.0695/ vCPU-hr
$0.0174/GiB-hr
Network
100Gbps
Baseline: 100 Gbps
Storage & EBS
7,500MB/s
Max: 240,000 IOPS

Technical Specifications & Limits

Hardware specs, container thresholds, and system limits

Compute & Processor

ProcessorAMD EPYC 7R13 Processor
Architecturex86_64 (x86_64)
vCPUs / Threads192 vCPUs
Physical Cores96
Clock Speed2.6 GHz
Intel AVX / AVX2No
Intel Turbo BoostNo
Bare MetalNo (Virtualized)

Performance & Benchmarks

CoreMark Score3,842,690
CoreMark / vCPU20,014 / core
FFmpeg Transcoding131 FPS
CoreMark per Dollar287,833 score / $
Cost per vCPU-hr$0.0695
Cost per GiB-hr$0.0174

Containers & Kubernetes

EKS Max Pods737 pods
Max ECS Tasks120 tasks
Max ENIs15
IPv4/v6 per ENI50
Total Addressable IPs750 total IPs
CNI Prefix DelegationSupported (High Density)

Networking & Bandwidth

Network Performance100 Gigabit
Baseline Bandwidth100 Gbps
Burst / Peak Bandwidth100 Gbps
Enhanced NetworkingYes
EFA SupportNo
IPv6 SupportNative Dual-Stack Supported

Storage & EBS Optimization

Storage ConfigurationNVMe SSD (7520 GB)
Local NVMe Disk7520 GB
EBS Baseline Throughput7500 MB/s
EBS Max Throughput7500 MB/s
EBS Baseline IOPS240,000
EBS Max / Burst IOPS240,000
Dedicated EBS Throughput60000 Mbps

GPU & Hardware Acceleration

GPU ModelNVIDIA L4
Accelerator Count8x GPU(s)
Total GPU Memory192.0 GB
Memory ArchitectureGDDR / HBM
CUDA Compute Capabilityv8.9
Acceleration RuntimesCUDA, TensorRT, cuDNN, PyTorch, PyJAX

Platform & Architecture Details

Hypervisor / SystemAWS Nitro System (PCIe Offload)
Nitro EnclavesSupported (Isolated security enclaves)
Normalization Factor16.58846918
Generation StatusCurrent Generation (Recommended)
Date Introduced2024-04-04

Regional Pricing Matrix

Live on-demand rates across all global AWS cloud regions
Lowest Price Region
$13.3504/ hr
US East (N. Virginia) (us-east-1)
Highest Price Region
$22.6930/ hr
South America (Sao Paulo) (sa-east-1)
Global Fleet Average
$16.3223/ hr
Across all active regions
Regional Coverage
20regions
Available worldwide
Linux — Available in all 20 regions
Region NameRegion CodeOn-Demand Price
Asia Pacific (Hyderabad)
ap-south-2$16.0311
Asia Pacific (Malaysia)
ap-southeast-5$16.8174
Asia Pacific (Mumbai)
ap-south-1$16.0311
Asia Pacific (Seoul)
ap-northeast-2$16.4159
Asia Pacific (Sydney)
ap-southeast-2$17.3582
Asia Pacific (Tokyo)
ap-northeast-1$19.3621
AWS GovCloud (US-East)
us-gov-east-1$16.8273
AWS GovCloud (US-West)
us-gov-west-1$16.8273
Canada (Central)
ca-central-1$14.8235
EU (Frankfurt)
eu-central-1$16.6946
EU (London)
eu-west-2$16.9468
EU (Paris)
eu-west-3$16.9468
EU (Stockholm)
eu-north-1$14.1599
Europe (Spain)
eu-south-2$14.0670
Europe (Zurich)
eu-central-2$17.9985
Middle East (UAE)
me-central-1$16.3934
South America (Sao Paulo)Highest
sa-east-1$22.6930
US East (N. Virginia)Lowest
us-east-1$13.3504
US East (Ohio)Lowest
us-east-2$13.3504
US West (Oregon)Lowest
us-west-2$13.3504