g6.4xlarge


Amazon EC2 instance g6.4xlarge with 16 vCPUs, 64 GiB RAM and 1 x NVIDIA L4 22.35 GiB. Available in 20 regions starting from $965.94 per month. A -37% cheaper alternative is available.
Instance Typeg6.4xlarge
Instance FamilyGPU instance
DetailsMachine Learning (ML), 3D visualizations, graphics-heavy remote workstations, 3D rendering, application streaming, video encoding, and server-side graphics tasks.

g – GPU (Graphics Processing Unit)
6 – Generation
4xlarge – Size
vCPUs16
Memory64 GiB
CPU Architecturex86_64
ProcessorAMD EPYC 7R13 Processor
Clock Speed3.4 GHz
Threads Per Core2
Accelerators
GPUyes
GPU NameL4
GPU ManufacturerNVIDIA
GPUs1
GPU Memory22.35 GiB
GPU Total Memory22.35 GiB
Inference Acceleratorno
Accelerator Memory24 GiB
FPGAno
Instances
Sizesg6.xlarge, g6.2xlarge, g6.4xlarge, g6.8xlarge, g6.12xlarge, g6.16xlarge, g6.24xlarge, g6.48xlarge
Generationsg3.4xlarge, g5.4xlarge, g6.4xlarge
Variantsg6e.4xlarge, g6f.4xlarge
SageMakerml.g6.4xlarge
Free Tierno
Burstableno
Hibernationno
Instance Storage1 x 600 GB NVMe SSD
EBS (Elastic Block Store)
EBS Optimizeddefault
Encryptionsupported
NVMerequired
Dedicated Throughput8000 MBps
Optimized Baseline Bandwidth8000 Mbps
Optimized Baseline Throughput1000 Mbps
Optimized Baseline Performance32000 IOPS
Optimized Max Performance32000 IOPS
Optimized Max Bandwidth8000 Mbps
Optimized Max Throughput1000 Mbps
Networking
Networking PerformanceUp to 25 Gigabit
Enhanced Networkingyes
Max Interfaces8
Max Cards1
IPv4 Addresses per Interface30
IPv6 Addresses per Interface30
IPv6 Supportyes
ENA Supportrequired
EFA Supportno
Encryption in Transit Supportyes
ENA SRD Supportno

Regional Availability

US
GovCloud (US-East) / us-gov-east-1
GovCloud (US-West) / us-gov-west-1
US East (Ohio) / us-east-2
US East (Virginia) / us-east-1
US West (N. California) / us-west-1
US West (Oregon) / us-west-2
Central America
Mexico (Central) / mx-central-1
Canada
Canada (Central) / ca-central-1
Canada West (Calgary) / ca-west-1
Europe
Europe (Ireland) / eu-west-1
Europe (London) / eu-west-2
Europe (Frankfurt) / eu-central-1
Europe (Milan) / eu-south-1
Europe (Paris) / eu-west-3
Europe (Spain) / eu-south-2
Europe (Stockholm) / eu-north-1
Europe (Zurich) / eu-central-2
Africa
Africa (Cape Town) / af-south-1
South America
South America (São Paulo) / sa-east-1
Asia Pacific
Asia Pacific (Hong Kong) / ap-east-1
Asia Pacific (Hyderabad) / ap-south-2
Asia Pacific (Jakarta) / ap-southeast-3
Asia Pacific (Malaysia) / ap-southeast-5
Asia Pacific (Melbourne) / ap-southeast-4
Asia Pacific (Mumbai) / ap-south-1
Asia Pacific (New Zealand) / ap-southeast-6
Asia Pacific (Osaka) / ap-northeast-3
Asia Pacific (Seoul) / ap-northeast-2
Asia Pacific (Singapore) / ap-southeast-1
Asia Pacific (Sydney) / ap-southeast-2
Asia Pacific (Taipei) / ap-east-2
Asia Pacific (Thailand) / ap-southeast-7
Asia Pacific (Tokyo) / ap-northeast-1
Middle East
Israel (Tel Aviv) / il-central-1
Middle East (Bahrain) / me-south-1
Middle East (UAE) / me-central-1

Regional Prices

US Dollar ($)
Per Hour
Linux
Shared Tenancy
On Demand
Geography
Region Name
Region
Savings Options
Instance Price
USUS East (Virginia)us-east-1compare1.3232
USUS East (Ohio)us-east-2compare1.3232
USUS West (Oregon)us-west-2compare1.3232
HiddenHiddenhidden-1compare1.3942
HiddenHiddenhidden-2compare1.4034
HiddenHiddenhidden-3compare1.4692
HiddenHiddenhidden-4compare1.5889
HiddenHiddenhidden-5compare1.5889
HiddenHiddenhidden-6compare1.6248
HiddenHiddenhidden-7compare1.6270
HiddenHiddenhidden-8compare1.6547
HiddenHiddenhidden-9compare1.6668
HiddenHiddenhidden-10compare1.6678
HiddenHiddenhidden-11compare1.6678
HiddenHiddenhidden-12compare1.6797
HiddenHiddenhidden-13compare1.6797
HiddenHiddenhidden-14compare1.7204
HiddenHiddenhidden-15compare1.7839
HiddenHiddenhidden-16compare1.9190
HiddenHiddenhidden-17compare2.2492
Activate subscription to see all regions and unlock awesome features  

Best AI models you can run on this instance

Top open-weight chat models ranked by Intelligence Index that fit in g6.4xlarge's 22 GB of GPU memory. VRAM is estimated from the parameter count at the selected quantization, so treat it as guidance rather than a guarantee.

Chat Models
FP16 (full precision)
Model
Creator
Intelligence
Total params
Active params
~VRAM
Qwen3.5 9BAlibaba logoAlibaba32.4#1469B—22 GB
Qwen3.5 4BAlibaba logoAlibaba27.1#1904B—10 GB
Motif 2 12.7B ReasoningMotif Technologies19.1#2707B—17 GB
7 more models fit on g6.4xlarge
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Similar Alternative Instances

Find Similar Instances In:
Instance Type
Region
vCPUs
Memory (GiB)
GPU Name
Instance Price
Price Diff %
g5g.4xlargeUS East (Virginia) (us-east-1)1632T4g0.8280-37%
g6f.4xlargeUS East (Virginia) (us-east-1)1664L40.9500-28%
g4dn.4xlargeUS East (Virginia) (us-east-1)1664T41.2040-9%
gr6.4xlargeUS East (Virginia) (us-east-1)16128L41.539216%
g5.4xlargeUS East (Virginia) (us-east-1)1664A10G1.624023%
Select your cookie preferences
We use cookies and similar tools to enhance your experience, provide our services, and make improvements. Approved third parties also use these tools to certain site features. More details available here Cookie Policy