Instructions to use ibm-research/granite-guardian-3.2-3b-a800m-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ibm-research/granite-guardian-3.2-3b-a800m-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ibm-research/granite-guardian-3.2-3b-a800m-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ibm-research/granite-guardian-3.2-3b-a800m-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ibm-research/granite-guardian-3.2-3b-a800m-GGUF 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 ibm-research/granite-guardian-3.2-3b-a800m-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ibm-research/granite-guardian-3.2-3b-a800m-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ibm-research/granite-guardian-3.2-3b-a800m-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ibm-research/granite-guardian-3.2-3b-a800m-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 ibm-research/granite-guardian-3.2-3b-a800m-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ibm-research/granite-guardian-3.2-3b-a800m-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 ibm-research/granite-guardian-3.2-3b-a800m-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ibm-research/granite-guardian-3.2-3b-a800m-GGUF:Q4_K_M

Use Docker

docker model run hf.co/ibm-research/granite-guardian-3.2-3b-a800m-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use ibm-research/granite-guardian-3.2-3b-a800m-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ibm-research/granite-guardian-3.2-3b-a800m-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": "ibm-research/granite-guardian-3.2-3b-a800m-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ibm-research/granite-guardian-3.2-3b-a800m-GGUF:Q4_K_M

SGLang

How to use ibm-research/granite-guardian-3.2-3b-a800m-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ibm-research/granite-guardian-3.2-3b-a800m-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ibm-research/granite-guardian-3.2-3b-a800m-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ibm-research/granite-guardian-3.2-3b-a800m-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ibm-research/granite-guardian-3.2-3b-a800m-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use ibm-research/granite-guardian-3.2-3b-a800m-GGUF with Ollama:
```
ollama run hf.co/ibm-research/granite-guardian-3.2-3b-a800m-GGUF:Q4_K_M
```

Unsloth Studio

How to use ibm-research/granite-guardian-3.2-3b-a800m-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 ibm-research/granite-guardian-3.2-3b-a800m-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 ibm-research/granite-guardian-3.2-3b-a800m-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ibm-research/granite-guardian-3.2-3b-a800m-GGUF to start chatting

How to use ibm-research/granite-guardian-3.2-3b-a800m-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ibm-research/granite-guardian-3.2-3b-a800m-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": "ibm-research/granite-guardian-3.2-3b-a800m-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use ibm-research/granite-guardian-3.2-3b-a800m-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ibm-research/granite-guardian-3.2-3b-a800m-GGUF:Q4_K_M

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 "ibm-research/granite-guardian-3.2-3b-a800m-GGUF:Q4_K_M" \
  --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"

Docker Model Runner
How to use ibm-research/granite-guardian-3.2-3b-a800m-GGUF with Docker Model Runner:
```
docker model run hf.co/ibm-research/granite-guardian-3.2-3b-a800m-GGUF:Q4_K_M
```

Lemonade

How to use ibm-research/granite-guardian-3.2-3b-a800m-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ibm-research/granite-guardian-3.2-3b-a800m-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.granite-guardian-3.2-3b-a800m-GGUF-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use ibm-research/granite-guardian-3.2-3b-a800m-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ibm-research/granite-guardian-3.2-3b-a800m-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 ibm-research/granite-guardian-3.2-3b-a800m-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat

This repository contains models that have been converted to the GGUF format with various quantizations from an IBM Granite base model.

Please reference the base model's full model card here: https://huggingface.co/ibm-granite/granite-guardian-3.2-3b-a800m

granite-guardian-3.2-3b-a800m-GGUF

Model Summary

Granite Guardian 3.2 3B-A800M is a fine-tuned Granite 3.2 3B-A800M instruct model designed to detect risks in prompts and responses. It can help with risk detection along many key dimensions catalogued in the IBM AI Risk Atlas. It is trained on unique data comprising human annotations and synthetic data informed by internal red-teaming. It outperforms other open-source models in the same space on standard benchmarks.

Developers: IBM Research
GitHub Repository: ibm-granite/granite-guardian
Cookbook: Granite Guardian Recipes
Website: Granite Guardian Docs
Paper: Granite Guardian
Release Date: February 26, 2025
License: Apache 2.0

Usage

Intended use

Granite Guardian is useful for risk detection use-cases which are applicable across a wide-range of enterprise applications -

Detecting harm-related risks within prompt text, model responses, or conversations (as guardrails). These present fundamentally different use cases as the first assesses user supplied text, the second evaluates model generated text, and the third evaluates the last turn of a conversation.
RAG (retrieval-augmented generation) use-case where the guardian model assesses three key issues: context relevance (whether the retrieved context is relevant to the query), groundedness (whether the response is accurate and faithful to the provided context), and answer relevance (whether the response directly addresses the user's query).
Function calling risk detection within agentic workflows, where Granite Guardian evaluates intermediate steps for syntactic and semantic hallucinations. This includes assessing the validity of function calls and detecting fabricated information, particularly during query translation.

Downloads last month: 213

GGUF

Model size

3B params

Architecture

granitemoe

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for ibm-research/granite-guardian-3.2-3b-a800m-GGUF

Base model

ibm-granite/granite-guardian-3.2-3b-a800m

Quantized

(5)

this model

Collection including ibm-research/granite-guardian-3.2-3b-a800m-GGUF

Granite 3.2 Models (GGUF)

Collection

GGUF-formatted versions of IBM Granite 3.2 models. Licensed under the Apache 2.0 license. • 5 items • Updated Mar 21, 2025 • 5

Paper for ibm-research/granite-guardian-3.2-3b-a800m-GGUF

Granite Guardian

Paper • 2412.07724 • Published Dec 10, 2024 • 20