Instructions to use FetchieAI/gemma-3-4b-lawft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use FetchieAI/gemma-3-4b-lawft 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 FetchieAI/gemma-3-4b-lawft:BF16
# Run inference directly in the terminal:
llama cli -hf FetchieAI/gemma-3-4b-lawft:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf FetchieAI/gemma-3-4b-lawft:BF16
# Run inference directly in the terminal:
llama cli -hf FetchieAI/gemma-3-4b-lawft:BF16

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 FetchieAI/gemma-3-4b-lawft:BF16
# Run inference directly in the terminal:
./llama-cli -hf FetchieAI/gemma-3-4b-lawft:BF16

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 FetchieAI/gemma-3-4b-lawft:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf FetchieAI/gemma-3-4b-lawft:BF16

Use Docker

docker model run hf.co/FetchieAI/gemma-3-4b-lawft:BF16

LM Studio
Jan
Ollama
How to use FetchieAI/gemma-3-4b-lawft with Ollama:
```
ollama run hf.co/FetchieAI/gemma-3-4b-lawft:BF16
```

Unsloth Studio

How to use FetchieAI/gemma-3-4b-lawft with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for FetchieAI/gemma-3-4b-lawft to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for FetchieAI/gemma-3-4b-lawft to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for FetchieAI/gemma-3-4b-lawft to start chatting

Docker Model Runner
How to use FetchieAI/gemma-3-4b-lawft with Docker Model Runner:
```
docker model run hf.co/FetchieAI/gemma-3-4b-lawft:BF16
```

Lemonade

How to use FetchieAI/gemma-3-4b-lawft with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull FetchieAI/gemma-3-4b-lawft:BF16

Run and chat with the model

lemonade run user.gemma-3-4b-lawft-BF16

List all available models

lemonade list

Atomic Chat

TL;DR

This is a GGUF version of Gemma 3 4B, fine-tuned on Traditional Chinese legal instructions using court decisions published by the Judicial Yuan of Taiwan. It is suitable for legal Q&A, judgment summarization, and legal document reasoning. Compatible with llama.cpp and Ollama.

Training Data

This model was trained using a curated dataset of 96,556 Taiwanese court decisions from 2021, each with available full text (JFULL) and downloadable PDF (JPDF), where tabular structures are clearly embedded. The dataset is designed for:

Table extraction
OCR pretraining for legal PDFs
Multimodal training (PDF + table reasoning)

Acknowledgments

Data collected from the publicly available Judicial Yuan open datasets (Taiwan).

Downloads last month: -

GGUF

Model size

4B params

Architecture

gemma3

Hardware compatibility

16-bit

Inference Providers NEW

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