Hugging Face's logo

tanuj437
/
nyayasetu-gemma4-gguf

GGUF
Model card Files
xet
 Community
How to use from
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 tanuj437/nyayasetu-gemma4-gguf
# Run inference directly in the terminal:
llama cli -hf tanuj437/nyayasetu-gemma4-gguf
Install from WinGet (Windows) 
winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tanuj437/nyayasetu-gemma4-gguf
# Run inference directly in the terminal:
llama cli -hf tanuj437/nyayasetu-gemma4-gguf
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 tanuj437/nyayasetu-gemma4-gguf
# Run inference directly in the terminal:
./llama-cli -hf tanuj437/nyayasetu-gemma4-gguf
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 tanuj437/nyayasetu-gemma4-gguf
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tanuj437/nyayasetu-gemma4-gguf
Use Docker 
docker model run hf.co/tanuj437/nyayasetu-gemma4-gguf
Quick Links

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

NyayaSetu Gemma4

NyayaSetu is a privacy-first Indian legal understanding assistant built using Gemma 4.

Features

  • FIR understanding
  • Legal notice explanation
  • Police procedure understanding
  • Citizen legal guidance
  • Hinglish + English support
  • Offline inference
  • GGUF quantized deployment

Base Model

google/gemma-4-26B-A4B-it

Fine-Tuning

LoRA post-training on:

  • Indian legal procedural data
  • FIR examples
  • legal notices
  • citizen-law interactions
  • structured legal datasets

Quantized Version

GGUF Q4_K_M included for:

  • llama.cpp
  • Ollama
  • offline inference

Disclaimer

This system provides legal information, not legal advice. Users should consult qualified lawyers for serious legal matters.

Downloads last month
-
GGUF
Model size
25B params
Architecture
gemma4
Hardware compatibility
Log In to add your hardware

We're not able to determine the quantization variants.

View all variants
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support