Instructions to use davidgeorge25/opengenedit-gemma-4-31b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use davidgeorge25/opengenedit-gemma-4-31b with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="davidgeorge25/opengenedit-gemma-4-31b",
	filename="dgene-q4km.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use davidgeorge25/opengenedit-gemma-4-31b 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 davidgeorge25/opengenedit-gemma-4-31b
# Run inference directly in the terminal:
llama cli -hf davidgeorge25/opengenedit-gemma-4-31b

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf davidgeorge25/opengenedit-gemma-4-31b
# Run inference directly in the terminal:
llama cli -hf davidgeorge25/opengenedit-gemma-4-31b

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 davidgeorge25/opengenedit-gemma-4-31b
# Run inference directly in the terminal:
./llama-cli -hf davidgeorge25/opengenedit-gemma-4-31b

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 davidgeorge25/opengenedit-gemma-4-31b
# Run inference directly in the terminal:
./build/bin/llama-cli -hf davidgeorge25/opengenedit-gemma-4-31b

Use Docker

docker model run hf.co/davidgeorge25/opengenedit-gemma-4-31b

LM Studio
Jan

vLLM

How to use davidgeorge25/opengenedit-gemma-4-31b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "davidgeorge25/opengenedit-gemma-4-31b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "davidgeorge25/opengenedit-gemma-4-31b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/davidgeorge25/opengenedit-gemma-4-31b

Ollama
How to use davidgeorge25/opengenedit-gemma-4-31b with Ollama:
```
ollama run hf.co/davidgeorge25/opengenedit-gemma-4-31b
```

Unsloth Studio

How to use davidgeorge25/opengenedit-gemma-4-31b 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 davidgeorge25/opengenedit-gemma-4-31b 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 davidgeorge25/opengenedit-gemma-4-31b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for davidgeorge25/opengenedit-gemma-4-31b to start chatting

Atomic Chat new
Docker Model Runner
How to use davidgeorge25/opengenedit-gemma-4-31b with Docker Model Runner:
```
docker model run hf.co/davidgeorge25/opengenedit-gemma-4-31b
```

Lemonade

How to use davidgeorge25/opengenedit-gemma-4-31b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull davidgeorge25/opengenedit-gemma-4-31b

Run and chat with the model

lemonade run user.opengenedit-gemma-4-31b-{{QUANT_TAG}}

List all available models

lemonade list

OpenGeneEdit — Gemma 4 31B Fine-tune

OpenGeneEdit is a domain-specific fine-tune of Gemma 4 31B for synthetic biology plasmid design. Describe a genetic circuit in natural language — the model returns structured biochemical reasoning and a nucleotide sequence in a compiler-ready format.

Gemma is a trademark of Google LLC.

Model Details

Base model: google/gemma-4-31B-it
Fine-tune type: SFT / LoRA (merged)
Quantization: Q4_K_M GGUF
Domain: Synthetic biology — plasmid architecture compiler
Training data: iGEM parts registry (Promoter, RBS, CDS, Terminator), compiler-shaped supervised examples

Intended Use

Designed for use with the OpenGeneEdit compiler. Point DGENE_GGUF_PATH at the downloaded .gguf file and run python3 server.py. Compatible with llama-cpp-python.

Not intended as a standalone chatbot. Outputs are research tools — wet-lab validation remains the researcher's responsibility.