M4 family · General Purposex86_64 · Intel/AMD

m4-megamem-28

The m4-megamem-28 machine type has 28 vCPUs and 372 GB of memory. Pricing for this instance starts at $2.21 per hour and $1614.64 monthly in the us-central1 region.

Updated June 16, 2026
vCPUs
28
Memory
372 GB
Network
Up to 32 Gbps
Storage
Persistent Disk

Save up to $807/mo on every m4-megamem-28

Connect Google Cloud — we'll find the optimal pricing model for your workload.

All pricing options

us-central1 · USD · monthly = 730 hrs
Prices exclude local taxes
TermHourlyMonthlySavings
On-Demand
$2.2118$1614.64 Baseline
1-Year Committed Use Discount (CUD)
$1.3050$952.64 -41%
3-Year Committed Use Discount (CUD)
$0.6635$484.39 -70%
Preemptible / Spot
$1.1059$807.34 -50%
You could save $807.30/mo on this instance with the right pricing model.
Find my savings

Monthly cost estimator

Estimate your spend based on actual usage.
730 h
1h365h730h (24/7)
1
Estimated monthly
$1614.64
730 hrs × $2.2118/hr × 1

Compute

x86_64 · Intel/AMD
vCPUs i28
Memory i372 GB
Physical processorIntel Emerald Rapids
Nested VirtualizationNot supported
Sole TenantNot supported
GPUNone
Within M4 family
m4-hypermem-16
16 vCPU
m4-megamem-28
28 vCPU
m4-hypermem-32
32 vCPU
m4-megamem-56
56 vCPU
m4-hypermem-64
64 vCPU
m4-ultramem-56
56 vCPU
m4-megamem-112
112 vCPU
m4-ultramem-112
112 vCPU
m4-megamem-224
224 vCPU
m4-ultramem-224
224 vCPU

Lock in this rate across your fleet — typically save 30–40%

Connect your Google Cloud account to apply this pricing logic to every running instance automatically.

Networking

Max egress bandwidth32 Gbps
Tier 1 bandwidth50 Gbps
Enhanced networking iYes (gvnic/virtio)
IPv6 supportYes (Dual-stack VPC)

Storage

Max persistent disks128
Max disk size512 TB
Local SSDsNo local SSD

Compare with another instance

vs.
Specm4-megamem-28m4-hypermem-16Δ
vCPUs2816-43%
Memory372 GB248 GB-33%
Hourly Price$2.2118$1.4258-36%
Monthly Price$1614.64$1040.84-36%
Cost optimization

GCP recommender alerts can cut this bill ~30-40%.

Connect your GCP account. We'll identify every underutilized m4.* instance and show exactly where downsizing, cleaning up orphaned disks, or shifting to CUDs saves money — with zero code changes.