Instructions to use trufae/granite3-instruct-8b-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use trufae/granite3-instruct-8b-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="trufae/granite3-instruct-8b-gguf",
	filename="granite3-instruct-8b-q4.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 trufae/granite3-instruct-8b-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf trufae/granite3-instruct-8b-gguf
# Run inference directly in the terminal:
llama-cli -hf trufae/granite3-instruct-8b-gguf

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf trufae/granite3-instruct-8b-gguf
# Run inference directly in the terminal:
llama-cli -hf trufae/granite3-instruct-8b-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 trufae/granite3-instruct-8b-gguf
# Run inference directly in the terminal:
./llama-cli -hf trufae/granite3-instruct-8b-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 trufae/granite3-instruct-8b-gguf
# Run inference directly in the terminal:
./build/bin/llama-cli -hf trufae/granite3-instruct-8b-gguf

Use Docker

docker model run hf.co/trufae/granite3-instruct-8b-gguf

LM Studio
Jan
Ollama
How to use trufae/granite3-instruct-8b-gguf with Ollama:
```
ollama run hf.co/trufae/granite3-instruct-8b-gguf
```

Unsloth Studio new

How to use trufae/granite3-instruct-8b-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 trufae/granite3-instruct-8b-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 trufae/granite3-instruct-8b-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for trufae/granite3-instruct-8b-gguf to start chatting

Pi new

How to use trufae/granite3-instruct-8b-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf trufae/granite3-instruct-8b-gguf

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": "trufae/granite3-instruct-8b-gguf"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use trufae/granite3-instruct-8b-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 trufae/granite3-instruct-8b-gguf

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 trufae/granite3-instruct-8b-gguf

Run Hermes

hermes

Docker Model Runner
How to use trufae/granite3-instruct-8b-gguf with Docker Model Runner:
```
docker model run hf.co/trufae/granite3-instruct-8b-gguf
```

Lemonade

How to use trufae/granite3-instruct-8b-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull trufae/granite3-instruct-8b-gguf

Run and chat with the model

lemonade run user.granite3-instruct-8b-gguf-{{QUANT_TAG}}

List all available models

lemonade list

Granite3 GGUF

Source: ibm-granite/granite-3.0-8b-instruct

Setup:

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
python -m venv venv
. venv/bin/activate
pip install .

Download the tensors:

from huggingface_hub import snapshot_download
model_id="ibm-granite/granite-3.0-8b-instruct"
snapshot_download(repo_id=model_id, local_dir="granite3",
                  local_dir_use_symlinks=False, revision="main")

Build the gguf:

python convert_hf_to_gguf.py --outfile granite3.gguf --outtype q8_0 granite3

Test with r2ai

r2ai -m "$PWD/granite3.gguf"

Downloads last month: 4

GGUF

Model size

8B params

Architecture

granite

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