Saudi SALLM Q9B V1 Demo

Saudi SALLM Q9B V1 Demo

Runs a Gradio research demo of a private adapter on the Qwen3.5-9B language model from a browser page, for people who test models on GPU hardware.

Made by Dr-Zeyad-Alghamdi 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 demo that combines the Qwen3.5-9B base model with an adapter repository named SALLM-Q9B-Private. The author labels it a research demonstration and says deployment is untested. It runs on GPU hardware at Hugging Face.

Who it suits: People who study or compare language models and want a short way to try one adapter in a browser.

Industry | Who uses it | How they use it | Example
Research | Language model researchers | Try an adapter on Qwen3.5-9B before deeper tests | Send a test message from the Space page
Education | Machine learning students | See how an adapter is attached to a base model | Read app.py and requirements.txt
Software | Developers building Gradio apps | Reuse the three-file layout | Point a copy at a different adapter

Anyone who needs a supported, tested product can skip it.

Where to use it:

• A browser, by visiting the Space on Hugging Face
• Windows, macOS or Linux with Python, for a copy on your own computer
• A local Gradio page, once app.py is running

Use case | Who | What they get back
Try the adapter | Researchers | Generated text from the demo
Study the setup | Students and developers | A short app with only three files

How to set it up:

• Python and pip on Windows, macOS or Linux
• GPU hardware, which the README says is required
• ADAPTER_REPO_ID set as a Space variable
• HF_TOKEN as a secret, only if the adapter repository is private

1. Install the Hugging Face hub package.
2. Download the Space with the hf command.
3. Move into the new folder.
4. Install gradio, then the packages listed in requirements.txt.
5. Start the app with Python.

pip install -U huggingface_hub
hf download Dr-Zeyad-Alghamdi/SALLM-Q9B-V1 --repo-type space --local-dir SALLM-Q9B-V1
cd SALLM-Q9B-V1
pip install gradio
pip install -r requirements.txt
python app.py

How to use it: Online, visit the Space on Hugging Face and use the interface that appears. On your own computer, run the start command and open the local page Gradio serves.

python app.py

Tool | What it does
app.py | Starts the Gradio interface
requirements.txt | Lists the Python packages to install
README.md | Holds the research note and the variable settings

Example: Visit the Space, enter a short question, and read the text the model generates. The reply comes from Qwen3.5-9B with the adapter in place, if the adapter repository loads.

For newcomers and experts: If you are new, start by visiting the Space and sending one short message. You will see at once whether the demo is running.

If you know the field, the app is only three files, and the adapter is pulled from a repository named by ADAPTER_REPO_ID. The listed models are a private adapter repository and Qwen3.5-9B. The Space is set to the zero-a10g hardware, so the trade-off is a GPU requirement and an untested deployment.

You visit the Gradio page
app.py runs on GPU hardware
It reads ADAPTER_REPO_ID
Qwen3.5-9B with the adapter answers

Good to know:

• Status: the author calls it a research demonstration and says deployment is untested
• Hardware: GPU hardware is required, and the Space is set to zero-a10g
• Variables: ADAPTER_REPO_ID is needed, HF_TOKEN is optional for private repositories
• License: apache-2
• Cost to run: GPU hardware, plus an HF_TOKEN only for a private adapter repository, no paid service is named
• Data it reaches: the adapter repository and the Qwen3.5-9B model on Hugging Face, plus the text you type
• Not for: production use, since the README calls the deployment untested

On Hugging Face, 13 November 2026

• Likes: 2
• Built with: gradio
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/Dr-Zeyad-Alghamdi/SALLM-Q9B-V1
• Files: https://huggingface.co/spaces/Dr-Zeyad-Alghamdi/SALLM-Q9B-V1/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.