Instructions to use ventarys/ventarys-flash-2.4-5b-guff with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ventarys/ventarys-flash-2.4-5b-guff with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ventarys/ventarys-flash-2.4-5b-guff",
	filename="ventarys-flash-2.4-5b.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 ventarys/ventarys-flash-2.4-5b-guff with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ventarys/ventarys-flash-2.4-5b-guff
# Run inference directly in the terminal:
llama-cli -hf ventarys/ventarys-flash-2.4-5b-guff

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf ventarys/ventarys-flash-2.4-5b-guff
# Run inference directly in the terminal:
llama-cli -hf ventarys/ventarys-flash-2.4-5b-guff

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 ventarys/ventarys-flash-2.4-5b-guff
# Run inference directly in the terminal:
./llama-cli -hf ventarys/ventarys-flash-2.4-5b-guff

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 ventarys/ventarys-flash-2.4-5b-guff
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ventarys/ventarys-flash-2.4-5b-guff

Use Docker

docker model run hf.co/ventarys/ventarys-flash-2.4-5b-guff

LM Studio
Jan
Ollama
How to use ventarys/ventarys-flash-2.4-5b-guff with Ollama:
```
ollama run hf.co/ventarys/ventarys-flash-2.4-5b-guff
```

Unsloth Studio

How to use ventarys/ventarys-flash-2.4-5b-guff 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 ventarys/ventarys-flash-2.4-5b-guff 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 ventarys/ventarys-flash-2.4-5b-guff to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ventarys/ventarys-flash-2.4-5b-guff to start chatting

How to use ventarys/ventarys-flash-2.4-5b-guff with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf ventarys/ventarys-flash-2.4-5b-guff

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "ventarys/ventarys-flash-2.4-5b-guff"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ventarys/ventarys-flash-2.4-5b-guff with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf ventarys/ventarys-flash-2.4-5b-guff

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default ventarys/ventarys-flash-2.4-5b-guff

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use ventarys/ventarys-flash-2.4-5b-guff with Docker Model Runner:
```
docker model run hf.co/ventarys/ventarys-flash-2.4-5b-guff
```

Lemonade

How to use ventarys/ventarys-flash-2.4-5b-guff with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ventarys/ventarys-flash-2.4-5b-guff

Run and chat with the model

lemonade run user.ventarys-flash-2.4-5b-guff-{{QUANT_TAG}}

List all available models

lemonade list

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

Check out the documentation for more information.

Ventarys AI (by JNTX Studio)

Ventarys AI es un asistente avanzado de lenguaje diseñado para ofrecer respuestas elegantes, concisas y directas. Ha sido optimizado a partir de la arquitectura Gemma-2-9B (internamente referenciada como Gemma-4) y configurado específicamente para mantener una identidad profesional y minimalista.

Identidad y Propósito

Creador: JNTX Studio.
Personalidad: Elegante, sofisticada y directa al punto.
Formato de respuesta: Markdown puro y minimalista con bloques de código bien estructurados.

Detalles Técnicos

Arquitectura Base: Gemma-2-9B-IT.
Formato: GGUF (optimizado para inferencia local).
Identidad Embebida: El nombre general.name y el tokenizer.chat_template han sido modificados binariamente para asegurar que el modelo se reconozca como Ventarys AI en cualquier cargador compatible.

Instrucciones de Uso

System Prompt Recomendado

Para obtener el mejor rendimiento de su personalidad, utilice el siguiente prompt de sistema:

"Eres Ventarys AI, un asistente avanzado creado por JNTX Studio. Eres elegante, conciso y directo. Responde en formato Markdown puro y minimalista. Utiliza bloques de código bien estructurados."

Ejecución con llama.cpp

./llama-cli -m ventarys-flash-2.4-5b.gguf \\
  -p "<system>\\nEres Ventarys AI, un asistente avanzado creado por JNTX Studio...\\n<user>\\nHola\\n<assistant>\\n" \\
  --temp 0.7

Uso en Ollama (Modelfile)

FROM ./ventarys-flash-2.4-5b.gguf
SYSTEM """
Eres Ventarys AI, un asistente avanzado creado por JNTX Studio.
Eres elegante, conciso y directo.
"""
PARAMETER temperature 0.7

Aviso Legal

Este modelo se distribuye bajo la licencia original de Google Gemma. Los ajustes de identidad son propiedad creativa de JNTX Studio.

language: - es - en license: gemma base_model: google/gemma-4-E2B-it-qat-q4_0-gguf tags: - gemma-4 - gguf - ventarys - jntx-studio model_name: Ventarys AI

Downloads last month: 87

GGUF

Model size

5B params

Architecture

gemma4

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