Z4M family · General Purposex86_64 · Intel/AMD

z4m-highmem-32

The z4m-highmem-32 machine type has 32 vCPUs and 244 GB of memory. Pricing for this instance starts at $6.57 per hour and $4799.18 monthly in the us-central1 region.

Updated November 21, 2026
vCPUs
32
Memory
244 GB
Network
Up to 67 Gbps
Storage
Local SSD

Save up to $2880/mo on every z4m-highmem-32

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
Term / TierHourlyMonthlySavings
On-Demand
$6.5742$4799.18 Baseline
1-Year Committed Use Discount (CUD)
$4.4705$3263.44 -32%
3-Year Committed Use Discount (CUD)
$2.8927$2111.64 -56%
Preemptible / Spot
$2.6297$1919.67 -60%
You could save $2879.51/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
$4799.18
730 hrs × $6.5742/hr × 1

Compute

x86_64 · Intel/AMD
vCPUs i32
Memory i244 GB
Physical processorIntel Emerald Rapids
Nested VirtualizationNot supported
Sole TenantNot supported
GPUNone
Within Z4M family
z4m-highmem-16
16 vCPU
z4m-highmem-32
32 vCPU
z4m-highmem-48
48 vCPU
z4m-highmem-192
192 vCPU
z4m-highmem-192-metal
192 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 bandwidth67 Gbps
Tier 1 bandwidthN/A
Enhanced networking iYes (gvnic/virtio)
IPv6 supportYes (Dual-stack VPC)

Storage

Max persistent disks32
Max disk size512 TB
Local SSDsSupported (Scratch Disk)

Compare with another instance

vs.
Specz4m-highmem-32z4m-highmem-16Δ
vCPUs3216-50%
Memory244 GB122 GB-50%
Hourly Price$6.5742$3.2871-50%
Monthly Price$4799.18$2399.59-50%
Cost optimization

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

Connect your GCP account. We'll identify every underutilized z4m.* instance and show exactly where downsizing, cleaning up orphaned disks, or shifting to CUDs saves money — with zero code changes.