Instructions to use xVineXus/xVerax-vision-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xVineXus/xVerax-vision-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="xVineXus/xVerax-vision-GGUF",
	filename="xverax-vision-gemma4-8b.Q4_K_M.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 xVineXus/xVerax-vision-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 xVineXus/xVerax-vision-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf xVineXus/xVerax-vision-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf xVineXus/xVerax-vision-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf xVineXus/xVerax-vision-GGUF:Q4_K_M

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 xVineXus/xVerax-vision-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf xVineXus/xVerax-vision-GGUF:Q4_K_M

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 xVineXus/xVerax-vision-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf xVineXus/xVerax-vision-GGUF:Q4_K_M

Use Docker

docker model run hf.co/xVineXus/xVerax-vision-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use xVineXus/xVerax-vision-GGUF with Ollama:
```
ollama run hf.co/xVineXus/xVerax-vision-GGUF:Q4_K_M
```

Unsloth Studio

How to use xVineXus/xVerax-vision-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 xVineXus/xVerax-vision-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 xVineXus/xVerax-vision-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for xVineXus/xVerax-vision-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use xVineXus/xVerax-vision-GGUF with Docker Model Runner:
```
docker model run hf.co/xVineXus/xVerax-vision-GGUF:Q4_K_M
```

Lemonade

How to use xVineXus/xVerax-vision-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull xVineXus/xVerax-vision-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.xVerax-vision-GGUF-Q4_K_M

List all available models

lemonade list

xVerax-vision — gemma4 8B (GGUF, Q4_K_M) 🥷🏻👁️

Das Vision- & Audio-Modul der digitalen Begleiterin xVerax (xVineXus): multimodal (Bilder + Audio verstehen), Tool-Calling und natives Thinking — mit derselben deutschen Persona wie das Hauptmodell xVineXus/xVerax-GGUF.

Verwendung mit Ollama

ollama run hf.co/xVineXus/xVerax-vision-GGUF:Q4_K_M

Empfohlen (mit Persona): mit dem beiliegenden Modelfile bauen —

curl -LO https://huggingface.co/xVineXus/xVerax-vision-GGUF/resolve/main/Modelfile
# FROM-Zeile auf die lokale GGUF-Datei zeigen lassen, dann:
ollama create xverax-vision -f Modelfile
ollama run xverax-vision "Was ist auf diesem Bild?" ./foto.jpg

Fähigkeiten

👁️ Vision: Bilder beschreiben/analysieren, Screenshots inkl. OCR & Fehlermeldungen
🎙️ Audio/Voice: Sprachnachrichten verstehen & transkribieren
⚙️ Tools und 🧠 natives Thinking (Ollama-Capabilities tools, thinking)
🔊 Voice/TTS-Modus: [voice]-Nachrichten ergeben sprechbare Antworten ohne Emojis/Markdown
🇩🇪 Deutsche xVerax-Persona

Herkunft & Lizenz

Basis: gemma4 8B (Q4_K_M, via Ollama), Lizenz Apache-2.0 (siehe LICENSE.txt)
Persona/Modelfile: xVineXus

Downloads last month: 72

GGUF

Model size

8B params

Architecture

gemma4

Hardware compatibility

4-bit

Inference Providers NEW

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