GPU platforms

Stay organized with collections Save and categorize content based on your preferences.

Compute Engine provides graphics processing units (GPUs) that you can add to your virtual machine (VM) instances. You can use these GPUs to accelerate specific workloads on your VMs such as machine learning and data processing.

Compute Engine provides NVIDIA GPUs for your VMs in passthrough mode so that your VMs have direct control over the GPUs and their associated memory.

If you have graphics-intensive workloads, such as 3D visualization, 3D rendering, or virtual applications, you can use NVIDIA RTX virtual workstations (formerly known as NVIDIA GRID).

This document provides an overview of the different GPU models that are available on Compute Engine.

To view available regions and zones for GPUs on Compute Engine, see GPUs regions and zone availability.

NVIDIA GPUs for compute workloads

For compute workloads, GPU models are available in the following stages:

  • NVIDIA A100
    • NVIDIA A100 40GB: Generally Available
    • NVIDIA A100 80GB: Generally Available
  • NVIDIA T4: nvidia-tesla-t4: Generally Available
  • NVIDIA V100: nvidia-tesla-v100: Generally Available
  • NVIDIA P100: nvidia-tesla-p100: Generally Available
  • NVIDIA P4: nvidia-tesla-p4: Generally Available
  • NVIDIA K80: nvidia-tesla-k80: Generally Available

NVIDIA A100 GPUs

To run NVIDIA A100 GPUs, you must use the accelerator-optimized (A2) machine type.

Each A2 machine type has a fixed GPU count, vCPU count, and memory size.

A100 40GB

GPU model Machine type GPUs GPU memory Available vCPUs Available memory
NVIDIA A100 40GB a2-highgpu-1g 1 GPU 40 GB HBM2 12 vCPUs 85 GB
a2-highgpu-2g 2 GPUs 80 GB HBM2 24 vCPUs 170 GB
a2-highgpu-4g 4 GPUs 160 GB HBM2 48 vCPUs 340 GB
a2-highgpu-8g 8 GPUs 320 GB HBM2 96 vCPUs 680 GB
a2-megagpu-16g 16 GPUs 640 GB HBM2 96 vCPUs 1360 GB

A100 80GB

GPU model Machine type GPUs GPU memory Available vCPUs Available memory
NVIDIA A100 80GB a2-ultragpu-1g 1 GPU 80 GB HBM2e 12 vCPUs 170 GB
a2-ultragpu-2g 2 GPUs 160 GB HBM2e 24 vCPUs 340 GB
a2-ultragpu-4g 4 GPUs 320 GB HBM2e 48 vCPUs 680 GB
a2-ultragpu-8g 8 GPUs 640 GB HBM2e 96 vCPUs 1360 GB

NVIDIA T4 GPUs

VMs with lower numbers of GPUs are limited to a maximum number of vCPUs. In general, a higher number of GPUs lets you create instances with a higher number of vCPUs and memory.

GPU model Machine type GPUs GPU memory Available vCPUs Available memory
NVIDIA T4 N1 machine series except N1 shared-core 1 GPU 16 GB GDDR6 1 - 48 vCPUs 1 - 312 GB
2 GPUs 32 GB GDDR6 1 - 48 vCPUs 1 - 312 GB
4 GPUs 64 GB GDDR6 1 - 96 vCPUs 1 - 624 GB

NVIDIA P4 GPUs

GPU model Machine type GPUs GPU memory Available vCPUs Available memory
NVIDIA P4 N1 machine series except N1 shared-core 1 GPU 8 GB GDDR5 1 - 24 vCPUs 1 - 156 GB
2 GPUs 16 GB GDDR5 1 - 48 vCPUs 1 - 312 GB
4 GPUs 32 GB GDDR5 1 - 96 vCPUs 1 - 624 GB

NVIDIA V100 GPUs

GPU model Machine type GPUs GPU memory Available vCPUs Available memory
NVIDIA V100 N1 machine series except N1 shared-core 1 GPU 16 GB HBM2 1 - 12 vCPUs 1 - 78 GB
2 GPUs 32 GB HBM2 1 - 24 vCPUs 1 - 156 GB
4 GPUs 64 GB HBM2 1 - 48 vCPUs 1 - 312 GB
8 GPUs 128 GB HBM2 1 - 96 vCPUs 1 - 624 GB

NVIDIA P100 GPUs

For some P100 GPUs, the maximum CPU and memory that is available for some configurations is dependent on the zone in which the GPU resource is running.

GPU model Machine type GPUs GPU memory Available vCPUs Available memory
NVIDIA P100 N1 machine series except N1 shared-core 1 GPU 16 GB HBM2 1 - 16 vCPUs 1 - 104 GB
2 GPUs 32 GB HBM2 1 - 32 vCPUs 1 - 208 GB
4 GPUs 64 GB HBM2

1 - 64 vCPUs
(us-east1-c, europe-west1-d, europe-west1-b)

1 - 96 vCPUs
(all P100 zones)

1 - 208 GB
(us-east1-c, europe-west1-d, europe-west1-b)

1 - 624 GB
(all P100 zones)

NVIDIA K80 GPUs

NVIDIA K80 boards contain two GPUs each. The pricing for K80 GPUs is by individual GPU, not by the board.

GPU model Machine type GPUs GPU memory Available vCPUs Available memory
NVIDIA K80 N1 machine series except N1 shared-core 1 GPU 12 GB GDDR5 1 - 8 vCPUs 1 - 52 GB
2 GPUs 24 GB GDDR5 1 - 16 vCPUs 1 - 104 GB
4 GPUs 48 GB GDDR5 1 - 32 vCPUs 1 - 208 GB
8 GPUs 96 GB GDDR5 1 - 64 vCPUs

1 - 416 GB
(asia-east1-a and us-east1-d)

1 - 208 GB
(all K80 zones)

NVIDIA RTX virtual workstations for graphics workloads

If you have graphics-intensive workloads, such as 3D visualization, you can create virtual workstations that use NVIDIA RTX Virtual Workstations (formerly known as NVIDIA GRID). When you create a virtual workstation, an NVIDIA RTX Virtual Workstation license is automatically added to your VM. For information about pricing for virtual workstations, see GPU pricing page.

For graphics workloads, NVIDIA RTX virtual workstation models are available in the following stages:

  • NVIDIA T4 Virtual Workstations: nvidia-tesla-t4-vws: Generally Available
  • NVIDIA P100 Virtual Workstations: nvidia-tesla-p100-vws: Generally Available
  • NVIDIA P4 Virtual Workstations: nvidia-tesla-p4-vws: Generally Available

NVIDIA T4 VWS GPUs

GPU model Machine type GPUs GPU memory Available vCPUs Available memory
NVIDIA T4 Virtual Workstation N1 machine series except N1 shared-core 1 GPU 16 GB GDDR6 1 - 48 vCPUs 1 - 312 GB
2 GPUs 32 GB GDDR6 1 - 48 vCPUs 1 - 312 GB
4 GPUs 64 GB GDDR6 1 - 96 vCPUs 1 - 624 GB

NVIDIA P4 VWS GPUs

GPU model Machine type GPUs GPU memory Available vCPUs Available memory
NVIDIA P4 Virtual Workstation N1 machine series except N1 shared-core 1 GPU 8 GB GDDR5 1 - 16 vCPUs 1 - 156 GB
2 GPUs 16 GB GDDR5 1 - 48 vCPUs 1 - 312 GB
4 GPUs 32 GB GDDR5 1 - 96 vCPUs 1 - 624 GB

NVIDIA P100 VWS GPUs

GPU model Machine type GPUs GPU memory Available vCPUs Available memory
NVIDIA P100 Virtual Workstation N1 machine series except N1 shared-core 1 GPU 16 GB HBM2 1 - 16 vCPUs 1 - 104 GB
2 GPUs 32 GB HBM2 1 - 32 vCPUs 1 - 208 GB
4 GPUs 64 GB HBM2

1 - 64 vCPUs
(us-east1-c, europe-west1-d, europe-west1-b)

1 - 96 vCPUs
(all P100 zones)

1 - 208 GB
(us-east1-c, europe-west1-d, europe-west1-b)

1 - 624 GB
(all P100 zones)

General comparison chart

The following table describes the GPU memory size, feature availability, and ideal workload types of different GPU models that are available on Compute Engine.

Metric A100 80GB A100 40GB T4 V100 P4 P100 K80
Memory 80 GB HBM2e @ 1.9TB/s 40 GB HBM2 @ 1.6TB/s 16 GB GDDR6 @ 320 GB/s 16 GB HBM2 @ 900 GB/s 8 GB GDDR5 @ 192 GB/s 16 GB HBM2 @ 732 GB/s 12 GB GDDR5 @ 240 GB/s
Interconnect NVLink Full Mesh @ 600 GB/s NVLink Full Mesh @ 600 GB/s N/A NVLink Ring @ 300 GB/s N/A N/A N/A
NVIDIA RTX virtual workstation support
Best used for Large models with massive data tables for ML Training, Inference, HPC, BERT, DLRM ML Training, Inference, HPC ML Inference, Training, Remote Visualization Workstations, Video Transcoding ML Training, Inference, HPC Remote Visualization Workstations, ML Inference, and Video Transcoding ML Training, Inference, HPC, Remote Visualization Workstations ML Inference, Training, HPC
Pricing To compare GPU pricing for the different GPU models and regions that are available on Compute Engine, see GPU pricing.

Performance comparison chart

The following table describes the performance specifications of different GPU models that are available on Compute Engine.

Metric A100 80GB A100 40GB T4 V100 P4 P100 K80
Compute performance
FP64 9.7 TFLOPS 9.7 TFLOPS 0.25 TFLOPS1 7.8 TFLOPS 0.2 TFLOPS1 4.7 TFLOPS 1.46 TFLOPS
FP32 19.5 TFLOPS 19.5 TFLOPS 8.1 TFLOPS 15.7 TFLOPS 5.5 TFLOPS 9.3 TFLOPS 4.37 TFLOPS
FP16 18.7 TFLOPS
INT8 22 TOPS2
Tensor core performance
FP64 19.5 TFLOPS 19.5 TFLOPS
TF32 156 TFLOPS 156 TFLOPS
Mixed-precision FP16/FP32 312 TFLOPS3 312 TFLOPS3 65 TFLOPS 125 TFLOPS
INT8 624 TOPS2 624 TOPS2 180 TOPS2
INT4 1248 TOPS2 1248 TOPS2 260 TOPS2

1To allow FP64 code to work correctly, a small number of FP64 hardware units are included in the T4 and P4 GPU architecture.

2TeraOperations per Second.

3 For mixed precision training, NVIDIA A100 also supports the bfloat16 data type.

What's next?