RWKV Gradio 4

RWKV Gradio 4

Runs a Gradio chatbot demo of RWKV models from BlinkDL in the browser on ZeroGPU hardware, with code for running a copy on your own computer.

Made by BlinkDL on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: This Space is a Gradio chatbot demo for RWKV models, made by BlinkDL. You open it in a browser and chat with an RWKV model without installing anything. The repository holds the app, a CUDA folder, a helper file for the RWKV7 model and a list of Python packages.

Who it suits: It suits people who want to try an RWKV model in a chat window, and developers who want the demo's code as a starting point.

Industry | Who uses it | How they use it | Example
Research | Language model researchers | Chat with an RWKV model to see how it responds | Try a few prompts on the hosted page
Software | Developers | Read app.py and the RWKV7 helper to see how the demo is wired | Copy the Space and change the chat interface
Education | Students of language models | Use the hosted chat to see a non-transformer style model in action | Compare it with another chat model

You can skip it if you want a finished assistant, since this is a model demo and its code.

Where to use it:

• A web browser: open the Space page on Hugging Face, where it runs on zero-a10g hardware.
• Windows, macOS or Linux: run a copy with Python 3.12.

Use case | Who | What they get back
Chat with the model | Anyone curious | Replies from an RWKV model in the browser
Study the code | Developers | The app, the CUDA folder and an RWKV7 helper file
Run a private copy | Developers | A copy that starts with python app.py

How to set it up: The hosted page needs nothing from you. A local copy needs these things first. The repository does not say what hardware a local copy needs.

• Python 3.12 on Windows, macOS or Linux.
• pip, which installs the packages.

1. Install the huggingface_hub package with pip.
2. Download the Space's files into a folder with the hf command.
3. Move into that folder.
4. Install Gradio 6.26.0, then the packages listed in requirements.txt.
5. Start the app with Python.

pip install -U huggingface_hub
hf download BlinkDL/RWKV-Gradio-4 --repo-type space --local-dir RWKV-Gradio-4
cd RWKV-Gradio-4
pip install gradio==6.26.0
pip install -r requirements.txt
python app.py

How to use it: Online, open the Space page and chat there. On your own computer, run the last command above inside the downloaded folder and use the chat it starts.

Tool | What it does
app.py | Starts the Gradio chat demo
rwkv7_fast_v3a.py | A helper file named for the RWKV7 model
cuda | A folder of CUDA code
requirements.txt | Lists the Python packages the app needs

Example: You open the Space page and type a short question into the chat box. An RWKV model answers in the same window. Running python app.py in your own copy gives you the same chat from your machine.

For newcomers and experts: If you are new, start with the hosted chat and send a few short messages. Nothing needs installing. Once that feels familiar, copy the Space to your computer.

If you know the field, the Space uses Gradio 6.26.0 on Python 3.12 and runs on ZeroGPU. It has a CUDA folder and an RWKV7 helper file, and it names two model repositories from BlinkDL. The README is the standard chatbot template, so it says little about the models.

Open the Space or run app.py
Gradio starts the chat interface
You chat with the RWKV model

Good to know: The README is a template text and does not describe the models, their sizes or their limits.

• License: apache-2
• Cost to run: none named, though the README mentions the Hugging Face Inference API
• Data it reaches: none named

On Hugging Face, 13 November 2026

• Likes: 8
• Built with: gradio
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/BlinkDL/RWKV-Gradio-4
• Files: https://huggingface.co/spaces/BlinkDL/RWKV-Gradio-4/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.