Instructions to use Open4bits/EXAONE-4.0-1.2B-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Open4bits/EXAONE-4.0-1.2B-gguf with Transformers:

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

pipe = pipeline("text-generation", model="Open4bits/EXAONE-4.0-1.2B-gguf")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Open4bits/EXAONE-4.0-1.2B-gguf", dtype="auto")

llama-cpp-python

How to use Open4bits/EXAONE-4.0-1.2B-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Open4bits/EXAONE-4.0-1.2B-gguf",
	filename="exaone-4.0-1.2B-Q4_0.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 Open4bits/EXAONE-4.0-1.2B-gguf with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Open4bits/EXAONE-4.0-1.2B-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Open4bits/EXAONE-4.0-1.2B-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 Open4bits/EXAONE-4.0-1.2B-gguf:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Open4bits/EXAONE-4.0-1.2B-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 Open4bits/EXAONE-4.0-1.2B-gguf:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Open4bits/EXAONE-4.0-1.2B-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 Open4bits/EXAONE-4.0-1.2B-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Open4bits/EXAONE-4.0-1.2B-gguf:Q4_K_M

Use Docker

docker model run hf.co/Open4bits/EXAONE-4.0-1.2B-gguf:Q4_K_M

LM Studio
Jan

vLLM

How to use Open4bits/EXAONE-4.0-1.2B-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Open4bits/EXAONE-4.0-1.2B-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": "Open4bits/EXAONE-4.0-1.2B-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Open4bits/EXAONE-4.0-1.2B-gguf:Q4_K_M

SGLang

How to use Open4bits/EXAONE-4.0-1.2B-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 "Open4bits/EXAONE-4.0-1.2B-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": "Open4bits/EXAONE-4.0-1.2B-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 "Open4bits/EXAONE-4.0-1.2B-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": "Open4bits/EXAONE-4.0-1.2B-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use Open4bits/EXAONE-4.0-1.2B-gguf with Ollama:
```
ollama run hf.co/Open4bits/EXAONE-4.0-1.2B-gguf:Q4_K_M
```

Unsloth Studio new

How to use Open4bits/EXAONE-4.0-1.2B-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 Open4bits/EXAONE-4.0-1.2B-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 Open4bits/EXAONE-4.0-1.2B-gguf to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Open4bits/EXAONE-4.0-1.2B-gguf to start chatting

Pi new

How to use Open4bits/EXAONE-4.0-1.2B-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf Open4bits/EXAONE-4.0-1.2B-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": "Open4bits/EXAONE-4.0-1.2B-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Open4bits/EXAONE-4.0-1.2B-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 Open4bits/EXAONE-4.0-1.2B-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 Open4bits/EXAONE-4.0-1.2B-gguf:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use Open4bits/EXAONE-4.0-1.2B-gguf with Docker Model Runner:
```
docker model run hf.co/Open4bits/EXAONE-4.0-1.2B-gguf:Q4_K_M
```

Lemonade

How to use Open4bits/EXAONE-4.0-1.2B-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Open4bits/EXAONE-4.0-1.2B-gguf:Q4_K_M

Run and chat with the model

lemonade run user.EXAONE-4.0-1.2B-gguf-Q4_K_M

List all available models

lemonade list

Open4bits / EXAONE-4.0-1.2B-GGUF

This repository provides the EXAONE-4.0-1.2B model converted to GGUF format, published by Open4bits to enable efficient local inference with reduced memory usage and broad CPU compatibility.

The underlying EXAONE model and architecture are developed and owned by LG AI Research. This repository contains only a quantized GGUF conversion of the original model weights.

The model is designed for lightweight text generation and instruction-following tasks, making it suitable for local and resource-constrained environments.

Model Overview

EXAONE 4.0 is a large language model family developed by LG AI Research, focusing on strong reasoning, instruction understanding, and multilingual capabilities. This release uses the 1.2B parameter variant, optimized for efficiency while retaining the original architecture.

The GGUF format allows seamless use with popular local inference engines and CPU-based runtimes.

Model Details

Architecture: EXAONE 4.0
Parameters: 1.2 billion
Format: GGUF (quantized)
Task: Text generation, instruction following
Languages: English, Korean, Spanish
Weight tying: Preserved
Compatibility: GGUF-compatible runtimes (CPU-focused inference)

Compared to larger EXAONE variants, this model prioritizes lower memory usage and faster inference, with some trade-off in reasoning depth.

Intended Use

This model is intended for:

Local text generation and chat applications
CPU-based or low-resource deployments
Research, experimentation, and prototyping
Offline or self-hosted AI systems

Limitations

Reduced performance compared to larger EXAONE models
Output quality depends on prompt design and inference settings
Not fine-tuned for highly specialized or domain-specific tasks

License

This repository follows the original EXAONE license terms as defined by LG AI Research. Users must comply with the licensing conditions of the base EXAONE-4.0-1.2B model.

Support

If you find this model useful, consider supporting the project. Your support helps Open4bits continue converting and releasing high-quality, efficient models for the community.

Downloads last month: 545

GGUF

Model size

1B params

Architecture

exaone4

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

16-bit

32-bit

Model tree for Open4bits/EXAONE-4.0-1.2B-gguf

Base model

LGAI-EXAONE/EXAONE-4.0-1.2B

Quantized

(33)

this model

Collection including Open4bits/EXAONE-4.0-1.2B-gguf

GGUF

Collection

28 items • Updated 23 days ago • 1