Instructions to use SciTools/granite with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use SciTools/granite 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 SciTools/granite:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf SciTools/granite:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf SciTools/granite:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf SciTools/granite:UD-Q4_K_XL

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 SciTools/granite:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf SciTools/granite:UD-Q4_K_XL

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 SciTools/granite:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SciTools/granite:UD-Q4_K_XL

Use Docker

docker model run hf.co/SciTools/granite:UD-Q4_K_XL

LM Studio
Jan
Ollama
How to use SciTools/granite with Ollama:
```
ollama run hf.co/SciTools/granite:UD-Q4_K_XL
```
Unsloth Desktop

How to use SciTools/granite with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SciTools/granite:UD-Q4_K_XL

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "SciTools/granite:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use SciTools/granite with Docker Model Runner:
```
docker model run hf.co/SciTools/granite:UD-Q4_K_XL
```

Lemonade

How to use SciTools/granite with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SciTools/granite:UD-Q4_K_XL

Run and chat with the model

lemonade run user.granite-UD-Q4_K_XL

List all available models

lemonade list

Hermes Agent

How to use SciTools/granite with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SciTools/granite:UD-Q4_K_XL

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 SciTools/granite:UD-Q4_K_XL

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use SciTools/granite with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf SciTools/granite:UD-Q4_K_XL

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "SciTools/granite:UD-Q4_K_XL" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Granite 4 GGUF

IBM Granite 4 models in GGUF format, for Understand's local AI. Understand serves them with its bundled server, ullama, which is built on llama.cpp.

To choose a model, see Choose a model in Understand's help. It compares every model Understand offers, with SciTools' test results and memory needs, and stays current. This page only lists the files.

File	In Understand	Copied unmodified from
`granite-4.1-3b-UD-Q4_K_XL.gguf`	Granite4.1-3B, the default model	unsloth/granite-4.1-3b-GGUF
`granite-4.1-3b-Q4_0.gguf`	An earlier Granite4.1-3B download, kept for installs that use it	ibm-granite/granite-4.1-3b-GGUF
`granite-4.0-micro-Q4_K_M.gguf`	Not in the model picker	unsloth/granite-4.0-micro-GGUF
`granite-4.0-1b-Q4_K_M.gguf`	Not in the model picker	ibm-granite/granite-4.0-1b-GGUF

Granite 4 is released by IBM under the Apache 2.0 license. This repository redistributes the files unmodified; it is not endorsed by IBM.

Downloads last month: 506

GGUF

Model size

2B params

Architecture

granite

Hardware compatibility

4-bit

Inference Providers NEW

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