g2-standard-16
Compute Engine · G2 family
The g2-standard-16 is a gpu & accelerated Compute Engine machine type with 16 vCPUs and 64 GiB of memory, 1 × NVIDIA L4, running on Intel Cascade Lake with up to 32 gbps networking, starting at $1.143 per hour on demand.
- vCPUs
- 16
- memory
- 64 GiB
- gpu
- 1× L4
- on-demand
- $1.147
- spot vm
- $0.6865
- 1-yr committed use
- $0.7227
dedicated
4 GiB per vCPU
24 GiB total
$837/mo · us-central1
−40% vs on-demand
−37% vs on-demand
g2-standard-16 price by region
18 regions · hourly list prices in USD · On-demand · Spot VM · 1-yr Committed use · 3-yr Committed use
| Northern Virginiaus-east4cheapestNorth America | $1.143 | $0.6086 | $0.7204 | $0.5146 |
| Iowaus-central1referenceNorth America | $1.147 | $0.6865 | $0.7227 | $0.5162 |
| Oregonus-west1North America | $1.147 | $0.6865 | $0.7227 | $0.5162 |
| South Carolinaus-east1North America | $1.147 | $0.6865 | $0.7227 | $0.5162 |
| Mumbaiasia-south1Asia | $1.194 | $0.6065 | $0.7523 | $0.5374 |
| Netherlandseurope-west4Europe | $1.206 | $0.7234 | $0.7596 | $0.5426 |
| Belgiumeurope-west1Europe | $1.263 | $0.7579 | $0.7958 | $0.5684 |
| Montréalnorthamerica-northeast1North America | $1.263 | $0.7522 | $0.7958 | $0.5684 |
| Torontonorthamerica-northeast2North America | $1.263 | $0.7539 | $0.7958 | $0.5684 |
| Las Vegasus-west4North America | $1.292 | $0.7733 | $0.814 | $0.5814 |
| Londoneurope-west2Europe | $1.306 | $0.7837 | $0.8229 | $0.5878 |
| Taiwanasia-east1Asia | $1.328 | $0.7959 | $0.8369 | $0.5978 |
| Frankfurteurope-west3Europe | $1.352 | $0.8072 | $0.8518 | $0.6084 |
| Singaporeasia-southeast1Asia | $1.415 | $0.8493 | $0.8916 | $0.6369 |
| Seoulasia-northeast3Asia | $1.473 | $0.4966 | $0.9281 | $0.663 |
| Tokyoasia-northeast1Asia | $1.473 | $0.7899 | $0.9281 | $0.663 |
| Zuricheurope-west6Europe | $1.553 | $0.9292 | $0.9781 | $0.6987 |
| Dammamme-central2Middle East | $1.836 | $1.033 | $1.156 | $0.826 |
Specifications
compute
- vCPUs
- 16
- Memory
- 64 GiB
- Memory per vCPU
- 4 GiB
- Processor
- Intel Cascade Lake
- CPU vendor
- Intel
- Architecture
- x86-64
- Clock speed
- 2.2 GHz (turbo 2.9 GHz)
- Burstable CPU
- No
storage & network
- Local storage
- Persistent disk (local SSD attachable)
- Network
- Up to 32 Gbps
- Peak bandwidth
- 32 Gbps
accelerators
- Model
- NVIDIA L4
- Count
- 1
- Memory (total)
- 24 GiB
- Architecture
- Ada Lovelace
- Vendor
- NVIDIA
google cloud details
- API name
g2-standard-16- Family
- G2
- Category
- GPU & accelerated
- Generation
- Current
- Regions
- 18 (Asia, Europe, Middle East, North America)
- Cheapest region
- Northern Virginia · $1.143/hr
- CoreMark score
- 223,514
- Max persistent disks
- 128
g2-standard-16 equivalents on other clouds
closest match by vCPU, memory, CPU architecture, accelerator and class · Linux on-demand in each provider's reference region
| Provider | Instance | vCPU | Memory | Processor | On-demand | vs g2-standard-16 |
|---|---|---|---|---|---|---|
| Google Cloud | g2-standard-16 | 16 | 64 GiB | 1 × NVIDIA L4 | $1.147 | – |
| AWS | g6.4xlarge | 16 | 64 GiB | 1 × NVIDIA L4 | $1.323 | +15% |
| g5.4xlargeNVIDIA A10G | 16 | 64 GiB | 1 × NVIDIA A10G | $1.624 | +42% | |
| Akamai | RTX4000 Ada x1 LargeNVIDIA RTX 4000 Ada | 16 | 64 GiB | 1 × NVIDIA RTX 4000 Ada | $0.96 | -16% |
G2 family sizes
| Size | vCPU | Memory | Accelerator | Local storage | On-demand | Monthly | Spot | 1-yr |
|---|---|---|---|---|---|---|---|---|
| g2-standard-4 | 4 | 16 GiB | 1 × NVIDIA L4 | – | $0.7068 | $516 | $0.423 | $0.4453 |
| g2-standard-8 | 8 | 32 GiB | 1 × NVIDIA L4 | – | $0.8536 | $623 | $0.5108 | $0.5378 |
| g2-standard-12 | 12 | 48 GiB | 1 × NVIDIA L4 | – | $1.00 | $730 | $0.5986 | $0.6303 |
| g2-standard-16 | 16 | 64 GiB | 1 × NVIDIA L4 | – | $1.147 | $837 | $0.6865 | $0.7227 |
| g2-standard-24 | 24 | 96 GiB | 2 × NVIDIA L4 | – | $2.001 | $1,461 | $1.197 | $1.261 |
| g2-standard-32 | 32 | 128 GiB | 1 × NVIDIA L4 | – | $1.734 | $1,266 | $1.038 | $1.093 |
| g2-standard-48 | 48 | 192 GiB | 4 × NVIDIA L4 | – | $4.002 | $2,921 | $2.395 | $2.521 |
| g2-standard-96 | 96 | 384 GiB | 8 × NVIDIA L4 | – | $8.003 | $5,842 | $4.789 | $5.042 |
g2-standard-16 FAQ
How much does g2-standard-16 cost?
g2-standard-16 costs $1.147 per hour on demand with Linux in Iowa (us-central1), about $837 per month. Across 18 regions the Linux on-demand price ranges from $1.143 in Northern Virginia to $1.836 in Dammam. Spot VM capacity costs $0.6865 per hour (40% less), but can be reclaimed. A 1-yr Committed use commitment brings it to $0.7227 per hour. With Windows it costs $1.883 per hour.
How many vCPUs and how much memory does g2-standard-16 have?
g2-standard-16 has 16 vCPUs and 64 GiB of memory (4 GiB per vCPU), running on Intel Cascade Lake. It is a gpu & accelerated machine type in the G2 family.
What is the cheapest region for g2-standard-16?
Northern Virginia (us-east4) at $1.143 per hour for Linux on demand. g2-standard-16 is sold in 18 Google Cloud regions.
What GPU does g2-standard-16 have?
g2-standard-16 has 1 × NVIDIA L4 with 24 GiB of accelerator memory in total.
What are the equivalents of g2-standard-16 on other clouds?
The closest matches by vCPU, memory, CPU architecture, accelerator and instance class are on AWS, g6.4xlarge (16 vCPU, 64 GiB, $1.323/hour in US East (N. Virginia)); on Akamai, RTX4000 Ada x1 Large (16 vCPU, 64 GiB, $0.96/hour in Newark, NJ).