Cerebras AI Day 🎉 March 19 🎉 San Jose
RSVP

Revolutionary Compute
for Generative AI

Go beyond the GPU. Train the most ambitious models in record time on Cerebras Wafer Scale Clusters.

Condor Galaxy AI Supercomputer

00

CS-2s

00

Exaflops

00

Million Cores

00

TB of RAM

00

Thread to Program

LEARN MORE

custom ai models

You bring the data, we'll train the model

Whether you want to build a multi-lingual chatbot or predict DNA sequences, our team of AI scientists and engineers will work with you and your data to build state-of-the-art models leveraging the latest AI techniques.

FIND OUT MORE

high performance computing

The fastest HPC accelerator on earth

With 850,000 cores and 40 GB of on-chip memory, the CS-2 completely redefines the performance envelope of HPC systems. From Monte Carlo Particle Transport to Seismic Processing, the CS-2 routinely outperforms entire supercomputing installations.

FIND OUT MORE

Models on Cerebras

The Cerebras platform has trained a huge assortment of models from multi-lingual LLMs to healthcare chatbots. We help customers train their own foundation models or fine-tune open source models like Llama 2. Best of all, the majority of our work is open source.

BTLM-chat

BTLM-3B-8K fine-tuned for chat
3B parameters, 8K context
Direct Preference Optimization

CRYSTALCODER

Trained for English + Code
7B Parameters, 1.3T Tokens
LLM360 Release

gigaGPT

Implements nanoGPT on Cerebras
Trains 175B+ models
565 lines of code

JAIS

Bilingual Arabic + English model
13B, 30B Parameters
Available on Azure, G42 Cloud

MED42

Medical Q&A LLM
Fine-tuned from Llama2-70B
Scores 72% on USMLE

llama 2

Foundation language model
7B-70B, 2T tokens
4K context

bloom

Massive multi-lingual LLM
176B parameters, 366B tokens
2k context

starcoder

Coding LLM
15.5B parameters, 1T tokens
8K context

diffusion
transformer

Image generation model
33M-2B parameters
Adaptive layer norm

T5

For NLP applications
Encoder-decoder model
60M-11B parameters

U-Net

Image segmentation model
2D and 3D variants
Up to 50M pixels

CEREBRAS-GPT

Foundational Language Model
100m - 13b parameters
NLP

Latest blog posts