Compare instance

g6.24xlarge

⚡ 4x GPU • 96 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.24xlarge24 Extra Large24xlarge = 24 Extra Large96 vCPUs • 384 GB RAM • 4 GB X 940 GB NVMe SSD • 50 Gbps Network • 4x NVIDIA L4 (96.0 GB VRAM)
Price (Linux)
$6.6752/ hr
~$4,872.90/mo
Compute
96vCPUs
48 cores • x86_64
Memory
384GB
4.0 GB / vCPU
Value
$0.0695/ vCPU-hr
$0.0174/GB-hr
Network
50 Gbps
Baseline: 50 Gbps
Storage & EBS
3,750MB/s
Max: 120,000 IOPS

Alternatives to g6.24xlarge

OptionPrice vs g6.24xlargeWhy look at it
g5.24xlargeCompare →
+22%+$1.47/hr
Linux on-demand, us-east-1		Previous generation, same vCPU and RAM
inf2.24xlargeCompare →
-3%-$0.185/hr
Linux on-demand, us-east-1		Older generation, same vCPU and RAM

Technical Specifications & Limits

Hardware specs, container thresholds, and system limits

Compute & Processor

ProcessorAMD EPYC 7R13 Processor
Architecturex86_64 (x86_64)
vCPUs / Threads96 vCPUs
Physical Cores48
Clock Speed2.6 GHz
Intel AVX / AVX2No
Intel Turbo BoostNo
Bare MetalNo (Virtualized)

Performance & Benchmarks

CoreMark Score1,884,200
CoreMark / vCPU19,627.1 / core
FFmpeg Transcoding134 FPS
CoreMark per Dollar282,269 score / $
Cost per vCPU-hr$0.0695
Cost per GB-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 Performance50 Gbps
Baseline Bandwidth50 Gbps
Burst / Peak Bandwidth50 Gbps
Enhanced NetworkingYes
EFA SupportNo
IPv6 SupportNative Dual-Stack Supported

Storage & EBS Optimization

Storage ConfigurationX 940 GB NVMe SSD (4 GB)
Local NVMe Disk4 GB X 940 GB NVMe SSD
EBS Baseline Throughput3750 MB/s
EBS Max Throughput3750 MB/s
EBS Baseline IOPS120,000
EBS Max / Burst IOPS120,000
Dedicated EBS Throughput30000 Mbps

GPU & Hardware Acceleration

GPU ModelNVIDIA L4
Accelerator Count4x GPU(s)
Total GPU Memory96.0 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 Factor8.294234592
Generation StatusCurrent Generation (Recommended)
Date Introduced2024-04-04

Regional Pricing Matrix

Live on-demand rates across all global AWS cloud regions
Lowest Price Region
$6.6752/ hr
US East (N. Virginia) (us-east-1)
Highest Price Region
$11.3465/ hr
South America (Sao Paulo) (sa-east-1)
Global Fleet Average
$8.1611/ hr
Across all active regions
Regional Coverage
20regions
Available worldwide
Linux — Available in all 20 regions
RegionOn-Demand Price
ap-south-2
Asia Pacific (Hyderabad)
$8.0155
ap-southeast-5
Asia Pacific (Malaysia)
$8.4087
ap-south-1
Asia Pacific (Mumbai)
$8.0155
ap-northeast-2
Asia Pacific (Seoul)
$8.2080
ap-southeast-2
Asia Pacific (Sydney)
$8.6791
ap-northeast-1
Asia Pacific (Tokyo)
$9.6810
us-gov-east-1
AWS GovCloud (US-East)
$8.4137
us-gov-west-1
AWS GovCloud (US-West)
$8.4137
ca-central-1
Canada (Central)
$7.4117
eu-central-1
EU (Frankfurt)
$8.3473
eu-west-2
EU (London)
$8.4734
eu-west-3
EU (Paris)
$8.4734
eu-north-1
EU (Stockholm)
$7.0800
eu-south-2
Europe (Spain)
$7.0335
eu-central-2
Europe (Zurich)
$8.9992
me-central-1
Middle East (UAE)
$8.1967
sa-east-1
South America (Sao Paulo)
Highest
$11.3465
us-east-1
US East (N. Virginia)
Lowest
$6.6752
us-east-2
US East (Ohio)
Lowest
$6.6752
us-west-2
US West (Oregon)
Lowest
$6.6752