g6.48xlarge


Amazon EC2 instance g6.48xlarge with 192 vCPUs, 768 GiB RAM and 8 x NVIDIA L4 22.35 GiB. Available in 20 regions starting from $9745.79 per month.
Instance Typeg6.48xlarge
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
48xlarge – Size
vCPUs192
Memory768 GiB
CPU Architecturex86_64
ProcessorAMD EPYC 7R13 Processor
Clock Speed3.4 GHz
Threads Per Core2
Accelerators
GPUyes
GPU NameL4
GPU ManufacturerNVIDIA
GPUs8
GPU Memory22.35 GiB
GPU Total Memory178.81 GiB
Inference Acceleratorno
Accelerator Memory192 GiB
FPGAno
Instances
Sizesg6.xlarge, g6.2xlarge, g6.4xlarge, g6.8xlarge, g6.12xlarge, g6.16xlarge, g6.24xlarge, g6.48xlarge
Generationsg5.48xlarge, g6.48xlarge, g7.48xlarge
Variantsg6e.48xlarge
SageMakerml.g6.48xlarge
Free Tierno
Burstableno
Hibernationno
Instance Storage8 x 940 NVMe SSD
EBS (Elastic Block Store)
EBS Optimizeddefault
Encryptionsupported
NVMerequired
Dedicated Throughput60000 MBps
Optimized Baseline Bandwidth60000 Mbps
Optimized Baseline Throughput7500 Mbps
Optimized Baseline Performance240000 IOPS
Optimized Max Performance240000 IOPS
Optimized Max Bandwidth60000 Mbps
Optimized Max Throughput7500 Mbps
Networking
Networking Performance100 Gigabit
Enhanced Networkingyes
Max Interfaces15
Max Cards1
IPv4 Addresses per Interface50
IPv6 Addresses per Interface50
IPv6 Supportyes
ENA Supportrequired
EFA Supportyes
EFA Max Interfaces1
Encryption in Transit Supportyes
ENA SRD Supportyes

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-1compare13.3504
USUS East (Ohio)us-east-2compare13.3504
USUS West (Oregon)us-west-2compare13.3504
HiddenHiddenhidden-1compare14.0670
HiddenHiddenhidden-2compare14.1599
HiddenHiddenhidden-3compare14.8235
HiddenHiddenhidden-4compare16.0311
HiddenHiddenhidden-5compare16.0311
HiddenHiddenhidden-6compare16.3934
HiddenHiddenhidden-7compare16.4160
HiddenHiddenhidden-8compare16.6946
HiddenHiddenhidden-9compare16.8174
HiddenHiddenhidden-10compare16.8273
HiddenHiddenhidden-11compare16.8273
HiddenHiddenhidden-12compare16.9468
HiddenHiddenhidden-13compare16.9468
HiddenHiddenhidden-14compare17.3582
HiddenHiddenhidden-15compare17.9985
HiddenHiddenhidden-16compare19.3621
HiddenHiddenhidden-17compare22.6930
Activate subscription to see all regions and unlock all features  

Best AI models you can run on this instance

Top open-weight chat models ranked by Intelligence Index that fit in g6.48xlarge's 179 GB of GPU memory, assuming the model is sharded across all 8 GPUs. 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
Qwen3.6 27BAlibaba logoAlibaba37.1#5427B—65 GB
Qwen3.5 27BAlibaba logoAlibaba33.8#7727B—65 GB
Qwen3.6 35B A3BAlibaba logoAlibaba31.6#9635B3B84 GB
7 more models fit on g6.48xlarge
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 %
g5.48xlargeUS East (Virginia) (us-east-1)192768A10G16.288022%
p4d.24xlargeUS East (Virginia) (us-east-1)961152A10021.957664%
g6e.48xlargeUS East (Virginia) (us-east-1)1921536L40S30.1312126%
p3dn.24xlargeUS East (Virginia) (us-east-1)96768V10031.2120134%
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