Instructions to use Apolo81/granite-4-350m-map-commands-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Apolo81/granite-4-350m-map-commands-gguf with Transformers.js:

// npm i @huggingface/transformers
import { pipeline } from '@huggingface/transformers';

// Allocate pipeline
const pipe = await pipeline('text-generation', 'Apolo81/granite-4-350m-map-commands-gguf');

llama-cpp-python

How to use Apolo81/granite-4-350m-map-commands-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Apolo81/granite-4-350m-map-commands-gguf",
	filename="granite-4-350m-map-commands-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Apolo81/granite-4-350m-map-commands-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Apolo81/granite-4-350m-map-commands-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Apolo81/granite-4-350m-map-commands-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 Apolo81/granite-4-350m-map-commands-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Apolo81/granite-4-350m-map-commands-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 Apolo81/granite-4-350m-map-commands-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Apolo81/granite-4-350m-map-commands-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 Apolo81/granite-4-350m-map-commands-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Apolo81/granite-4-350m-map-commands-gguf:Q4_K_M

Use Docker

docker model run hf.co/Apolo81/granite-4-350m-map-commands-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use Apolo81/granite-4-350m-map-commands-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Apolo81/granite-4-350m-map-commands-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Apolo81/granite-4-350m-map-commands-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Apolo81/granite-4-350m-map-commands-gguf:Q4_K_M

Ollama
How to use Apolo81/granite-4-350m-map-commands-gguf with Ollama:
```
ollama run hf.co/Apolo81/granite-4-350m-map-commands-gguf:Q4_K_M
```

Unsloth Studio new

How to use Apolo81/granite-4-350m-map-commands-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 Apolo81/granite-4-350m-map-commands-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 Apolo81/granite-4-350m-map-commands-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Apolo81/granite-4-350m-map-commands-gguf to start chatting

Pi new

How to use Apolo81/granite-4-350m-map-commands-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Apolo81/granite-4-350m-map-commands-gguf:Q4_K_M

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": "Apolo81/granite-4-350m-map-commands-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Apolo81/granite-4-350m-map-commands-gguf with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Apolo81/granite-4-350m-map-commands-gguf:Q4_K_M

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 Apolo81/granite-4-350m-map-commands-gguf:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use Apolo81/granite-4-350m-map-commands-gguf with Docker Model Runner:
```
docker model run hf.co/Apolo81/granite-4-350m-map-commands-gguf:Q4_K_M
```

Lemonade

How to use Apolo81/granite-4-350m-map-commands-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Apolo81/granite-4-350m-map-commands-gguf:Q4_K_M

Run and chat with the model

lemonade run user.granite-4-350m-map-commands-gguf-Q4_K_M

List all available models

lemonade list

🚀 Granite 4.0-H-350M - Map Commands (GGUF)

Modelo IBM Granite 4.0-H-350M fine-tunado para comandos de mapa em português, convertido para formato GGUF.

📊 Informações do Modelo

Arquitetura: Granite Hybrid (4 Transformer + 28 Mamba2 layers)
Tamanho Base: 350M parâmetros
Idioma: Português (PT-BR)
Especialização: Tool calling para 12 ferramentas de mapa
Formato: GGUF (Q4_K_M e Q8_0)
Acurácia: 100% nos testes de treinamento

📦 Versões Disponíveis

Arquivo	Tamanho	Descrição
`granite-4-350m-map-commands-Q4_K_M.gguf`	~175MB	Recomendado para mobile/tablets
`granite-4-350m-map-commands-Q8_0.gguf`	~340MB	Melhor qualidade

🎯 12 Tools Treinadas

abrir_pin - Abrir marcador no mapa
fechar_pin - Fechar marcador
abrir_todos_pins - Mostrar todos os marcadores
fechar_todos_pins - Esconder todos os marcadores
expandir_mapa - Expandir mapa para tela cheia
minimizar_mapa - Minimizar mapa
recentralizar_mapa - Voltar para centro
mostrar_regiao - Focar em região específica
abrir_menu - Abrir menu lateral
fechar_menu - Fechar menu lateral
mostrar_stats - Mostrar estatísticas
listar_servicos - Listar serviços disponíveis

🚀 Uso com Transformers.js

Downloads last month: 51

GGUF

Model size

0.4B params

Architecture

granite

Hardware compatibility

4-bit

8-bit

Model tree for Apolo81/granite-4-350m-map-commands-gguf

Base model

ibm-granite/granite-4.0-h-350m-base

Finetuned

ibm-granite/granite-4.0-h-350m

Quantized

(42)

this model