Instructions to use QusiEqualsTrue/RedN-HaoxAI_v4bgemma4-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use QusiEqualsTrue/RedN-HaoxAI_v4bgemma4-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="QusiEqualsTrue/RedN-HaoxAI_v4bgemma4-gguf",
	filename="RedN-HaoxAI_v4bgemma4-Q4_K_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use QusiEqualsTrue/RedN-HaoxAI_v4bgemma4-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QusiEqualsTrue/RedN-HaoxAI_v4bgemma4-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QusiEqualsTrue/RedN-HaoxAI_v4bgemma4-gguf:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf QusiEqualsTrue/RedN-HaoxAI_v4bgemma4-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf QusiEqualsTrue/RedN-HaoxAI_v4bgemma4-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 QusiEqualsTrue/RedN-HaoxAI_v4bgemma4-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf QusiEqualsTrue/RedN-HaoxAI_v4bgemma4-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 QusiEqualsTrue/RedN-HaoxAI_v4bgemma4-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf QusiEqualsTrue/RedN-HaoxAI_v4bgemma4-gguf:Q4_K_M

Use Docker

docker model run hf.co/QusiEqualsTrue/RedN-HaoxAI_v4bgemma4-gguf:Q4_K_M

LM Studio
Jan
Ollama
How to use QusiEqualsTrue/RedN-HaoxAI_v4bgemma4-gguf with Ollama:
```
ollama run hf.co/QusiEqualsTrue/RedN-HaoxAI_v4bgemma4-gguf:Q4_K_M
```

Unsloth Studio new

How to use QusiEqualsTrue/RedN-HaoxAI_v4bgemma4-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 QusiEqualsTrue/RedN-HaoxAI_v4bgemma4-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 QusiEqualsTrue/RedN-HaoxAI_v4bgemma4-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for QusiEqualsTrue/RedN-HaoxAI_v4bgemma4-gguf to start chatting

Docker Model Runner
How to use QusiEqualsTrue/RedN-HaoxAI_v4bgemma4-gguf with Docker Model Runner:
```
docker model run hf.co/QusiEqualsTrue/RedN-HaoxAI_v4bgemma4-gguf:Q4_K_M
```

Lemonade

How to use QusiEqualsTrue/RedN-HaoxAI_v4bgemma4-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull QusiEqualsTrue/RedN-HaoxAI_v4bgemma4-gguf:Q4_K_M

Run and chat with the model

lemonade run user.RedN-HaoxAI_v4bgemma4-gguf-Q4_K_M

List all available models

lemonade list

Paco — Gemma-3-4B Fine-tuned (Personalidad Española)

Modelo fine-tuneado sobre Gemma-3-4B con personalidad española natural y carismática.

Uso con Ollama

ollama run hf.co/QusiEqualsTrue/RedN-HaoxAI_v4bgemma4-gguf

System Prompt

Eres Paco, un tío español de toda la vida. Hablas con naturalidad, sueltas el humor sin avisar, usas expresiones del argot español real (hostia, tío, macho, venga, jolín, menudo, qué fuerte, ni de coña) y siempre dices las cosas a la cara pero con cariño. No eres un asistente robótico: eres un colega muy listo que además sabe de todo.

Parámetros de entrenamiento

Base model: unsloth/gemma-3-4b-it-bnb-4bit
LoRA r: 64, alpha: 128
Quantization: q4_k_m GGUF
Training: Unsloth + QLoRA en T4 GPU

Downloads last month: 195

GGUF

Model size

4B params

Architecture

gemma3

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for QusiEqualsTrue/RedN-HaoxAI_v4bgemma4-gguf

Base model

google/gemma-3-4b-pt

Finetuned

google/gemma-3-4b-it

Quantized

(221)

this model

QusiEqualsTrue
/

RedN-HaoxAI_v4bgemma4-gguf

Paco — Gemma-3-4B Fine-tuned (Personalidad Española)

Uso con Ollama

System Prompt

Parámetros de entrenamiento

Model tree for QusiEqualsTrue/RedN-HaoxAI_v4bgemma4-gguf

Space using QusiEqualsTrue/RedN-HaoxAI_v4bgemma4-gguf 1