Instructions to use Open4bits/llama3.2-1b-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Open4bits/llama3.2-1b-gguf with Transformers:

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

pipe = pipeline("text-generation", model="Open4bits/llama3.2-1b-gguf")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Open4bits/llama3.2-1b-gguf", dtype="auto")

llama-cpp-python

How to use Open4bits/llama3.2-1b-gguf with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Open4bits/llama3.2-1b-gguf",
	filename="llama3.2-1b-F16.gguf",
)

output = llm(
	"Once upon a time,",
	max_tokens=512,
	echo=True
)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Open4bits/llama3.2-1b-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/llama3.2-1b-gguf:F16
# Run inference directly in the terminal:
llama-cli -hf Open4bits/llama3.2-1b-gguf:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Open4bits/llama3.2-1b-gguf:F16
# Run inference directly in the terminal:
llama-cli -hf Open4bits/llama3.2-1b-gguf:F16

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/llama3.2-1b-gguf:F16
# Run inference directly in the terminal:
./llama-cli -hf Open4bits/llama3.2-1b-gguf:F16

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/llama3.2-1b-gguf:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Open4bits/llama3.2-1b-gguf:F16

Use Docker

docker model run hf.co/Open4bits/llama3.2-1b-gguf:F16

LM Studio
Jan

vLLM

How to use Open4bits/llama3.2-1b-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Open4bits/llama3.2-1b-gguf"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Open4bits/llama3.2-1b-gguf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Open4bits/llama3.2-1b-gguf:F16

SGLang

How to use Open4bits/llama3.2-1b-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/llama3.2-1b-gguf" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Open4bits/llama3.2-1b-gguf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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/llama3.2-1b-gguf" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Open4bits/llama3.2-1b-gguf",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use Open4bits/llama3.2-1b-gguf with Ollama:
```
ollama run hf.co/Open4bits/llama3.2-1b-gguf:F16
```

Unsloth Studio new

How to use Open4bits/llama3.2-1b-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/llama3.2-1b-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/llama3.2-1b-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/llama3.2-1b-gguf to start chatting

Docker Model Runner
How to use Open4bits/llama3.2-1b-gguf with Docker Model Runner:
```
docker model run hf.co/Open4bits/llama3.2-1b-gguf:F16
```

Lemonade

How to use Open4bits/llama3.2-1b-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Open4bits/llama3.2-1b-gguf:F16

Run and chat with the model

lemonade run user.llama3.2-1b-gguf-F16

List all available models

lemonade list

Open4bits / llama3.2-1b-gguf

This repository provides the LLaMA 3.2-1B model converted to GGUF format, published by Open4bits to enable highly efficient local inference with reduced memory usage and broad CPU compatibility.

The underlying LLaMA 3.2 model and architecture are owned by Meta AI. This repository contains only a quantized GGUF conversion of the original model weights.

The model is designed for fast, lightweight text generation and instruction-following tasks and is well suited for resource-constrained environments.

Model Overview

LLaMA (Large Language Model Meta AI) is a family of transformer-based language models developed by Meta AI. This release uses the 3.2 variant with 1 billion parameters, striking a balance between performance and efficiency.

Model Details

Architecture: LLaMA 3.2
Parameters: ~1 billion
Format: GGUF (quantized)
Task: Text generation, instruction following
Weight tying: Preserved
Compatibility: GGUF-compatible inference runtimes (CPU-focused)

Compared to larger LLaMA variants, this model offers significantly faster inference with lower memory requirements, with proportionally reduced capacity for complex reasoning.

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

Lower generation quality compared to larger LLaMA 3.2 models
Output quality depends on prompt design and decoding settings
Not fine-tuned for domain-specific or high-precision tasks

License

This model is released under the original LLaMA 3.2 license terms as defined by Meta AI. Users must comply with the licensing conditions of the base LLaMA 3.2-1B model.

Support

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

Downloads last month: 25

GGUF

Model size

1B params

Architecture

llama

Hardware compatibility

8-bit

16-bit

32-bit

Model tree for Open4bits/llama3.2-1b-gguf

Base model

meta-llama/Llama-3.2-1B

Quantized

(244)

this model

Collection including Open4bits/llama3.2-1b-gguf

GGUF

Collection

28 items • Updated 18 days ago • 1