Lambda Inference

Inference Server for Deep Learning

12-GPU / 16-GPU / 20-GPU Options

Trusted by Top A.I. Research Groups

Apple is a customer Microsoft is a customer IBM is a customer Berkeley is a customer MIT is a customer

Most Popular Options

Customize From Scratch

Basic

12x Tesla T4 GPUs

In Stock (Ships in 2-3 Days)
2x Xeon Silver 4116 (12 Cores, 2.10 GHz)
12x NVIDIA T4 (16 GB)
256 GB RAM
Fully Customizable Storage
10 Gbps Ethernet
Lambda Support Contract - 1 year
Starting at
$ 41,529
Customize
Premium

16x Tesla T4 GPUs

In Stock (Ships in 2-3 Days)
2x Xeon Gold 6148 (20 cores, 2.40 GHz)
16x NVIDIA T4 (16 GB)
512 GB RAM
Fully Customizable Storage
100 Gbps InfiniBand
Lambda Support Contract - 1 year
Starting at
$ 60,558
Customize
Max

20x Tesla T4 GPUs

In Stock (Ships in 2-3 Days)
2x Xeon Platinum 8168 (24 Cores, 2.70 GHz)
20x NVIDIA T4 (16 GB)
512 GB RAM
Fully Customizable Storage
100 Gbps InfiniBand
Lambda Support Contract - 3 years
Starting at
$ 77,486
Customize
custom

In Stock (Ships in 2-3 Days)
Starting at
$
Customize

Zero Setup, Easy Updates

Lambda Stack comes free with your computer. Machine Learning libraries work out-of-the box and can be updated automatically.

Explore Lambda's Research

Our research papers have been accepted into the top machine learning and graphics conferences, including ICCV, SIGGRAPH Asia, NeurIPS, and ACM Transactions on Graphics (TOG).

HoloGAN: Unsupervised Learning of 3D Representations from Natural Images
We propose a novel generative adversarial network (GAN) for the task of unsupervised learning of 3D representations from natural images. Learn More
RenderNet: A Deep Conv. Network for Differentiable Rendering from 3D Shapes
Traditional computer graphics rendering pipelines are designed for procedurally generating 2D images from 3D shapes with high performance. Learn More
Adversarial Monte Carlo Denoising with Conditioned Aux. Feature Modulation
Denoising Monte Carlo rendering with a very low sample rate remains a major challenge in the photo-realistic rendering research. Learn More