FreeAIRepo
LLMs & chat

Zefan-Cai/R-KV

[Neurips 2025] R-KV: Redundancy-aware KV Cache Compression for Reasoning Models

Python
Open on GitHub Website
Stars
1.2k
Forks
196
Open issues
4
Last push
3d ago

About R-KV

R-KV is a free, open-source LLM chat app by Zefan-Cai, written mainly in Python. [Neurips 2025] R-KV: Redundancy-aware KV Cache Compression for Reasoning Models. It has 1.2k GitHub stars and 196 forks, and was last updated 3d ago. GitHub doesn't detect a standard license, so check the repository before using it commercially.

License
Not detected
Language
Python
Stars
1,219
Last update
3d ago
Runs on Mac
Not stated
GPU
Not stated
Paid API key
Not required
Self-hostable
Not stated

Similar free tools

All LLMs & chat tools →

R-KV FAQ

Is R-KV free?

Yes. R-KV is open source and free to use. GitHub doesn't detect a standard license, so check the repository before using it commercially.

Does R-KV run on a Mac?

The project doesn't say. Check its installation guide before you start.

Does R-KV need a GPU?

The project doesn't state hardware needs. AI models generally run much faster with a GPU.

Is R-KV still maintained?

Yes. It was last updated 3d ago and has 4 open issues on GitHub.

What are alternatives to R-KV?

Similar free, open-source tools include Hands-On-Large-Language-Models, self-llm, Open-LLM-VTuber, Qwen.

Related topics

kvcachellmreasoning-modelsr kv