Home Projects mergekit
mergekit
Python

mergekit

Tools for merging pretrained large language models.

by arcee-ai · GitHub
Stars
Forks
License
Created
Last commit
Category
Language
Likely
Self-hostable
llamallmmodel-mergingLGPL-3.0PythonSelf-hostable
View on GitHub
In plain words

Merge different pre-trained language models efficiently, even on computers with limited resources.

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 →
mergekit — GitHub preview card
📈 Star history
7.3k7.2k
2026-07-042026-08-31
📈 Track mergekit

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

Tools for merging pretrained large language models.

mergekit has 7.3k stars on GitHub. It has been forked 788 times. mergekit is written mainly in Python. It has been in active development since 2023. mergekit is available under the LGPL-3.0 license. Its main topics are llama, llm, model-merging.

Frequently asked questions

What is mergekit?

Tools for merging pretrained large language models.

Is mergekit open source?

mergekit is an open-source project. It is released under the LGPL-3.0 license.

Is mergekit free?

Yes. mergekit is free and open source — you can use, modify and self-host it. Its LGPL-3.0 license is copyleft: if you distribute a modified version, it must remain under the same license.

What license does mergekit use?

mergekit is available under the LGPL-3.0 license.

What language is mergekit written in?

mergekit is written mainly in Python.

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

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

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

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