Instructions to use ruslanmv/granite-3.1-8b-Reasoning-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ruslanmv/granite-3.1-8b-Reasoning-GGUF with Transformers:

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

pipe = pipeline("text-generation", model="ruslanmv/granite-3.1-8b-Reasoning-GGUF")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ruslanmv/granite-3.1-8b-Reasoning-GGUF", device_map="auto")

llama-cpp-python

How to use ruslanmv/granite-3.1-8b-Reasoning-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="ruslanmv/granite-3.1-8b-Reasoning-GGUF",
	filename="unsloth.Q4_K_M.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use ruslanmv/granite-3.1-8b-Reasoning-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 ruslanmv/granite-3.1-8b-Reasoning-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ruslanmv/granite-3.1-8b-Reasoning-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 ruslanmv/granite-3.1-8b-Reasoning-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ruslanmv/granite-3.1-8b-Reasoning-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 ruslanmv/granite-3.1-8b-Reasoning-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ruslanmv/granite-3.1-8b-Reasoning-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 ruslanmv/granite-3.1-8b-Reasoning-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ruslanmv/granite-3.1-8b-Reasoning-GGUF:Q4_K_M

Use Docker

docker model run hf.co/ruslanmv/granite-3.1-8b-Reasoning-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use ruslanmv/granite-3.1-8b-Reasoning-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ruslanmv/granite-3.1-8b-Reasoning-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": "ruslanmv/granite-3.1-8b-Reasoning-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ruslanmv/granite-3.1-8b-Reasoning-GGUF:Q4_K_M

SGLang

How to use ruslanmv/granite-3.1-8b-Reasoning-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 "ruslanmv/granite-3.1-8b-Reasoning-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": "ruslanmv/granite-3.1-8b-Reasoning-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 "ruslanmv/granite-3.1-8b-Reasoning-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": "ruslanmv/granite-3.1-8b-Reasoning-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use ruslanmv/granite-3.1-8b-Reasoning-GGUF with Ollama:
```
ollama run hf.co/ruslanmv/granite-3.1-8b-Reasoning-GGUF:Q4_K_M
```

Unsloth Studio

How to use ruslanmv/granite-3.1-8b-Reasoning-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 ruslanmv/granite-3.1-8b-Reasoning-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 ruslanmv/granite-3.1-8b-Reasoning-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for ruslanmv/granite-3.1-8b-Reasoning-GGUF to start chatting

How to use ruslanmv/granite-3.1-8b-Reasoning-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ruslanmv/granite-3.1-8b-Reasoning-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": "ruslanmv/granite-3.1-8b-Reasoning-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use ruslanmv/granite-3.1-8b-Reasoning-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 ruslanmv/granite-3.1-8b-Reasoning-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 ruslanmv/granite-3.1-8b-Reasoning-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use ruslanmv/granite-3.1-8b-Reasoning-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ruslanmv/granite-3.1-8b-Reasoning-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 "ruslanmv/granite-3.1-8b-Reasoning-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 ruslanmv/granite-3.1-8b-Reasoning-GGUF with Docker Model Runner:
```
docker model run hf.co/ruslanmv/granite-3.1-8b-Reasoning-GGUF:Q4_K_M
```

Lemonade

How to use ruslanmv/granite-3.1-8b-Reasoning-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ruslanmv/granite-3.1-8b-Reasoning-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.granite-3.1-8b-Reasoning-GGUF-Q4_K_M

List all available models

lemonade list

Granite-3.1-8B-Reasoning-GGUF (Quantized for Efficient Inference)

Model Overview

This is a GGUF quantized version of ruslanmv/granite-3.1-8b-Reasoning, fine-tuned from ibm-granite/granite-3.1-8b-instruct. The GGUF format enables efficient inference on CPUs and GPUs, optimized for various K-bit quantization levels (4-bit, 5-bit, and 8-bit).

Developed by: ruslanmv
License: Apache 2.0
Base Model: ibm-granite/granite-3.1-8b-instruct
Fine-tuned for: Logical reasoning, structured problem-solving, long-context tasks
Quantized GGUF versions available:
- 4-bit: Q4_K_M
- 5-bit: Q5_K_M
- 8-bit: Q8_0
Supported Languages: English
Architecture: Granite
Model Size: 8.17B params

Why Use the GGUF Quantized Version?

The GGUF format is designed for optimized CPU and GPU inference, making it ideal for:

✅ Lower memory usage for efficient deployment
✅ Faster inference speeds on consumer hardware
✅ Compatibility with leading inference engines like llama.cpp, ctransformers, and KoboldCpp
✅ Improved performance on logical reasoning and analytical tasks

Installation & Usage

Install dependencies for llama.cpp:

pip install llama-cpp-python

Running the Model with llama.cpp:

from llama_cpp import Llama

model_path = "path/to/ruslanmv/granite-3.1-8b-Reasoning-GGUF.Q4_K_M.gguf"

llm = Llama(model_path=model_path)

input_text = "Can you explain the difference between inductive and deductive reasoning?"
output = llm(input_text, max_tokens=400)

print(output["choices"][0]["text"])

Alternatively, using ctransformers:

pip install ctransformers

from ctransformers import AutoModelForCausalLM

model_path = "path/to/ruslanmv/granite-3.1-8b-Reasoning-GGUF.Q4_K_M.gguf"

model = AutoModelForCausalLM.from_pretrained(model_path, model_type="llama", gpu_layers=50)

input_text = "What are the key principles of logical reasoning?"
output = model(input_text, max_new_tokens=400)

print(output)

Intended Use

Granite-3.1-8B-Reasoning-GGUF is designed for efficient inference while maintaining strong reasoning capabilities, making it ideal for:

Logical and analytical problem-solving
Text-based reasoning tasks
Mathematical and symbolic reasoning
Advanced instruction-following

This model is particularly beneficial for CPU-based deployments, low-memory environments, and users who need optimized text generation without requiring high-end GPUs.

License & Acknowledgments

This model is released under the Apache 2.0 license. It is fine-tuned from IBM’s Granite 3.1-8B-Instruct model and quantized using GGUF for optimal efficiency. Special thanks to the IBM Granite Team for developing the base model.

For more details, visit the IBM Granite Documentation.

Citation

If you use this model in your research or applications, please cite:

@misc{ruslanmv2025granite,
  title={Fine-Tuning and GGUF Quantization of Granite-3.1-8B for Advanced Reasoning},
  author={Ruslan M.V.},
  year={2025},
  url={https://huggingface.co/ruslanmv/granite-3.1-8b-Reasoning-GGUF}
}

Downloads last month: 88

GGUF

Model size

8B params

Architecture

granite

Hardware compatibility

4-bit

5-bit

8-bit

Model tree for ruslanmv/granite-3.1-8b-Reasoning-GGUF

Base model

ibm-granite/granite-3.1-8b-base

Finetuned

ibm-granite/granite-3.1-8b-instruct

Quantized

(30)

this model