g2-standard-48
$4.0017/hr
~$2921.22/month on-demand in us-central1
The g2-standard-48 is an Accelerator optimized instance with 48 vCPUs and 192 GiB of memory, 4x NVIDIA nvidia-l4 with up to 32 Gbps bandwidth, starting at $4.002 per hour or $2.945 per hour with spot instances.
Last updated: Jan 14, 2026, 09:17 PM UTC
Pricing Options
CUD
Committed Use Discounts
1 Year
$3.3499/hr
~$2445.43/mo
Save 16%
3 Year
$3.0328/hr
~$2213.97/mo
Save 24%
Spot Pricing
Up to 90% savings - flexible workloads
Spot Price
$2.9450/hr
~$2149.84/mo
Save 26%
g2-standard family
Switch between sizes in us-central1
| Size | vCPU | Mem |
|---|---|---|
| g2-standard-4 | 4 | 16 |
| g2-standard-8 | 8 | 32 |
| g2-standard-12 | 12 | 48 |
| g2-standard-16 | 16 | 64 |
| g2-standard-24 | 24 | 96 |
| g2-standard-32 | 32 | 128 |
| g2-standard-48 | 48 | 192 |
| g2-standard-96 | 96 | 384 |
Instance Specifications
Detailed hardware and capabilities for g2-standard-48
Processor
Architecturex86_64
vCPUs48
Memory192 GiB
Memory per vCPU4.00 GiB
Network
PerformanceUp to 32 Gbps
Bandwidth32 Gbps
Max Interfaces8
Enhanced Networking
Storage
Persistent Disk Only
GPU
Count4
ManufacturerNVIDIA
Modelnvidia-l4
Memory24 GiB
Total GPU Memory96 GiB
Capabilities
Familyg2-standard
GenerationCurrent
Burstable
Regional Pricing Comparison
Compare g2-standard-48 (Linux) pricing across all regions - sorted by cost
Current region (us-central1)Other regions
💡 Click any bar to open that region in a new tab