Home Projects ctransformers
ctransformers
C

ctransformers

Python bindings for the Transformer models implemented in C/C++ using GGML library.

by marella · GitHub
Stars
Forks
License
Created
Last commit
Category
Language
aictransformersllmMITC
View on GitHub
In plain words

Run various AI models using Python with a simple interface that connects to C/C++ implementations.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
ctransformers — GitHub preview card
📈 Star history
1.89k1.88k
2026-07-202026-08-31
📈 Track ctransformers

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

Python bindings for the Transformer models implemented in C/C++ using GGML library.

ctransformers has 1.9k stars on GitHub. It has been forked 143 times. ctransformers is written mainly in C. It has been in active development since 2023. ctransformers is available under the MIT license. Its main topics are ai, ctransformers, llm, transformers.

Frequently asked questions

What is ctransformers?

Python bindings for the Transformer models implemented in C/C++ using GGML library.

Is ctransformers open source?

ctransformers is an open-source project. It is released under the MIT license.

Is ctransformers free?

Yes. ctransformers is free and open source — you can use, modify and self-host it.

What license does ctransformers use?

ctransformers is available under the MIT license.

What language is ctransformers written in?

ctransformers is written mainly in C.

🏅 Maintainer of this project?
olud.ai badge — ctransformers

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=marella-ctransformers)](https://olud.ai/project/marella-ctransformers.html)
More badge options →
🧬 Shares DNA with

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.