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

Libraries

How to use wnduss/multimodal_lora_gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="wnduss/multimodal_lora_gguf",
	filename="model.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use wnduss/multimodal_lora_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 wnduss/multimodal_lora_gguf
# Run inference directly in the terminal:
llama cli -hf wnduss/multimodal_lora_gguf

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf wnduss/multimodal_lora_gguf
# Run inference directly in the terminal:
llama cli -hf wnduss/multimodal_lora_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 wnduss/multimodal_lora_gguf
# Run inference directly in the terminal:
./llama-cli -hf wnduss/multimodal_lora_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 wnduss/multimodal_lora_gguf
# Run inference directly in the terminal:
./build/bin/llama-cli -hf wnduss/multimodal_lora_gguf

Use Docker

docker model run hf.co/wnduss/multimodal_lora_gguf

LM Studio
Jan
Ollama
How to use wnduss/multimodal_lora_gguf with Ollama:
```
ollama run hf.co/wnduss/multimodal_lora_gguf
```

Unsloth Studio

How to use wnduss/multimodal_lora_gguf 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 wnduss/multimodal_lora_gguf 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 wnduss/multimodal_lora_gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for wnduss/multimodal_lora_gguf to start chatting

Atomic Chat new
Docker Model Runner
How to use wnduss/multimodal_lora_gguf with Docker Model Runner:
```
docker model run hf.co/wnduss/multimodal_lora_gguf
```

Lemonade

How to use wnduss/multimodal_lora_gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull wnduss/multimodal_lora_gguf

Run and chat with the model

lemonade run user.multimodal_lora_gguf-{{QUANT_TAG}}

List all available models

lemonade list

Multimodal LoRA (GGUF Format)

이 레포지토리는 파인튜닝된 Gemma3 LoRA 모델을 GGUF 포맷으로 변환한 파일입니다. llama.cpp, LM Studio, Ollama 등 다양한 로컬 추론 도구에서 바로 사용할 수 있습니다.

File Information

Source Model: wnduss/multimodal_lora
Quantization: f16 (원본 가중치 보존)

How to use

이 GGUF 파일은 아래 도구들에서 불러와 사용할 수 있습니다:

LM Studio: 모델 파일을 다운로드 후 검색창에 파일 경로를 입력하세요.
llama.cpp: 아래 명령어로 실행할 수 있습니다:

   ./main -m model.gguf -p "입력 프롬프트"

Downloads last month: 426

GGUF

Model size

4B params

Architecture

gemma3

Hardware compatibility

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