g4-standard-192


GCP g4-standard-192 - Graphics Optimized: 4 NVIDIA RTX PRO 6000 GPU, 192 vCPUs, 720GB RAM. Available in 20 regions starting from $13139.80 per month. A -47% cheaper alternative is available.
Instance Typeg4-standard-192
DetailsAccelerator Optimized for Graphics-intensive workloads, Video streaming and transcoding, remote virtual workstations, digital twins Inference.

g – Graphics-intensive workloads
4 – Generation
standard – 4x RAM/CPU ratio
192 – Number of CPUs
Instance FamilyAccelerator optimized
DescriptionGraphics Optimized: 4 NVIDIA RTX PRO 6000 GPU, 192 vCPUs, 720GB RAM
vCPUs192
Memory720 GiB
CPU Architecturex86_64
ProcessorAMD EPYC Turin
Shared CPUno
GPUyes
GPUs4
GPU Namenvidia-rtx-pro-6000
GPU Total RAM (GiB)384
Sustained Discounts (SUDs)no
Sole Tenancyno
Nested Virtualizationno
Custom Shapesno
Confidential Computeno
Maximum Persistent Disks64
Maximum Persistent Disks Size524288 GB
Disk Interface TypeNVMe
Local SSDyes
Max Local SSD12000 GB
Extreme Persistent Disksno
Hyperdisk Extremeyes
Hyperdisk Throughputyes
Network InterfacesgVNIC

Regional Availability

North America
California / us-west2
Iowa / us-central1
Mexico / northamerica-south1
Nevada / us-west4
Ohio / us-east5
Ontario / northamerica-northeast2
Oregon / us-west1
Québec / northamerica-northeast1
South Carolina / us-east1
Texas / us-south1
Utah / us-west3
Virginia / us-east4
Europe
Belgium / europe-west1
England / europe-west2
Finland / europe-north1
France / europe-west9
Germany / europe-west10
Germany / europe-west3
Italy / europe-west12
Italy / europe-west8
Netherlands / europe-west4
Poland / europe-central2
Spain / europe-southwest1
Sweden / europe-north2
Switzerland / europe-west6
APAC
Australia / australia-southeast1
Australia / australia-southeast2
Hong Kong / asia-east2
India / asia-south1
India / asia-south2
Indonesia / asia-southeast2
Japan / asia-northeast1
Japan / asia-northeast2
Singapore / asia-southeast1
South Korea / asia-northeast3
Taiwan / asia-east1
Middle East
Israel / me-west1
Qatar / me-central1
Saudi Arabia / me-central2
Africa
South Africa / africa-south1
South America
Brazil / southamerica-east1
Chile / southamerica-west1

Regional Prices

US Dollar ($)
Per Hour
On Demand
Geography
Region Name
Region
Savings Options
Instance Price
HiddenHiddenhidden-1compare17.9997
HiddenHiddenhidden-2compare17.9997
North AmericaIowaus-central1compare17.9997
North AmericaSouth Carolinaus-east1compare17.9997
North AmericaVirginiaus-east4compare17.9997
HiddenHiddenhidden-3compare19.7997
HiddenHiddenhidden-4compare19.7997
HiddenHiddenhidden-5compare19.7997
HiddenHiddenhidden-6compare19.7997
HiddenHiddenhidden-7compare19.7997
HiddenHiddenhidden-8compare19.7997
HiddenHiddenhidden-10compare21.5964
HiddenHiddenhidden-9compare21.5964
HiddenHiddenhidden-11compare21.5997
HiddenHiddenhidden-12compare21.5997
HiddenHiddenhidden-13compare21.5997
HiddenHiddenhidden-14compare23.3984
HiddenHiddenhidden-15compare23.3984
HiddenHiddenhidden-16compare23.3996
HiddenHiddenhidden-17compare23.3996
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 g4-standard-192's 384 GB of GPU memory, assuming the model is sharded across all 4 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
DeepSeek V4 FlashDeepSeek logoDeepSeek51.8#28158B—379 GB
Qwen3.6 27BAlibaba logoAlibaba37.7#8827B—65 GB
Qwen3.5 27BAlibaba logoAlibaba34.6#11327B—65 GB
7 more models fit on g4-standard-192
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)
Instance Price
Price Diff %
c4-standard-192-lssdIowa (us-central1)1927209.4882-47%