Instructions to use jdaddyalbs/qwen3_sft_playwright_gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use jdaddyalbs/qwen3_sft_playwright_gguf with Transformers:

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("jdaddyalbs/qwen3_sft_playwright_gguf", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use jdaddyalbs/qwen3_sft_playwright_gguf with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jdaddyalbs/qwen3_sft_playwright_gguf:Q8_0
# Run inference directly in the terminal:
llama cli -hf jdaddyalbs/qwen3_sft_playwright_gguf:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf jdaddyalbs/qwen3_sft_playwright_gguf:Q8_0
# Run inference directly in the terminal:
llama cli -hf jdaddyalbs/qwen3_sft_playwright_gguf:Q8_0

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf jdaddyalbs/qwen3_sft_playwright_gguf:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf jdaddyalbs/qwen3_sft_playwright_gguf:Q8_0

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf jdaddyalbs/qwen3_sft_playwright_gguf:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf jdaddyalbs/qwen3_sft_playwright_gguf:Q8_0

Use Docker

docker model run hf.co/jdaddyalbs/qwen3_sft_playwright_gguf:Q8_0

LM Studio
Jan
Ollama
How to use jdaddyalbs/qwen3_sft_playwright_gguf with Ollama:
```
ollama run hf.co/jdaddyalbs/qwen3_sft_playwright_gguf:Q8_0
```
Unsloth Desktop

How to use jdaddyalbs/qwen3_sft_playwright_gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jdaddyalbs/qwen3_sft_playwright_gguf:Q8_0

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "jdaddyalbs/qwen3_sft_playwright_gguf:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use jdaddyalbs/qwen3_sft_playwright_gguf with Docker Model Runner:
```
docker model run hf.co/jdaddyalbs/qwen3_sft_playwright_gguf:Q8_0
```

Lemonade

How to use jdaddyalbs/qwen3_sft_playwright_gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull jdaddyalbs/qwen3_sft_playwright_gguf:Q8_0

Run and chat with the model

lemonade run user.qwen3_sft_playwright_gguf-Q8_0

List all available models

lemonade list

Hermes Agent

How to use jdaddyalbs/qwen3_sft_playwright_gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jdaddyalbs/qwen3_sft_playwright_gguf:Q8_0

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default jdaddyalbs/qwen3_sft_playwright_gguf:Q8_0

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use jdaddyalbs/qwen3_sft_playwright_gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf jdaddyalbs/qwen3_sft_playwright_gguf:Q8_0

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "jdaddyalbs/qwen3_sft_playwright_gguf:Q8_0" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Description

This model was trained to be better at tool calling a playwright mcp server. Most people do not have compute resources to run the top LLMs. The goal here is to allow a smaller LLM to specialize at a specific task by copying successful demonstrations of a bigger LLM. To examine the data generation head to my dataset repo https://huggingface.co/jdaddyalbs/playwright-mcp-toolcalling.

My training code for this model is in the trainer-v1.ipynb, you will need to install additional dependencies like unsloth (look at the import statements at the top)

Getting Started

Install dependencies (ollama, uv, git, npx, google-chrome)

curl -LsSf https://astral.sh/uv/install.sh | sh
curl -fsSL https://ollama.com/install.sh | sh
sudo apt install git, npx, google-chrome
npx @playwright/mcp@latest

let npx install playwright then hit ctl+c to exit

Clone this repo and install python dependencies

git clone https://huggingface.co/jdaddyalbs/qwen3_sft_playwright_gguf
cd qwen3_sft_playwright_gguf
uv sync

Pull the model into Ollama using 1 of 2 ways

ollama pull hf.co/jdaddyalbs/qwen3_sft_playwright_gguf (use this method for the benchmark models like hf.co/unsloth/Qwen3-4B-GGUF:Q8_0)
ollama create hf.co/jdaddyalbs/qwen3_sft_playwright_gguf -f Modelfile

Run Evaluation

We will evaluate in two parts, first we will let the models use playwright to answer the eval queries, next we will check their answers against the ground truth answers and to see if they had a correct answer.

Part 1 playwright interaction

If you are using openai models you must get an API key and set it as environment variable before running.

export OPENAI_API_KEY="PASTE_YOUR_KEY_HERE"

If everything is installed correctly you should be able to run the following from this directory

uv run evaluate-v1.py

You will see chrome browsers opening up for a while and results will be appended to a 'results.jsonl' file.

Part 2 grade answers

Edit evaluate-part2-v1.py to use your best ollama model for grading the results (I use qwen3:32b). It also will expect a results.jsonl file from eval part 1. When everything is ready run the following:

uv run evaluate-part2-v1.py

The output of this should be a csv file called eval_results.csv this you can open in excel of libreoffice to view the results.

Results

Pending....

Uploaded model

Developed by: jdaddyalbs
License: apache-2.0
Finetuned from model : unsloth/qwen3-4b-bnb-4bit

This qwen3 model was trained 2x faster with Unsloth and Huggingface's TRL library.

Downloads last month: 166

GGUF

Model size

4B params

Architecture

qwen3

Hardware compatibility

8-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support