---
title: DFloat11 - Lossless LLM Compression for Efficient GPU Inference
emoji: ⚡
colorFrom: red
colorTo: gray
sdk: static
pinned: false
---

# ⚡️ DFloat11: Lossless LLM Compression for Efficient GPU Inference

DFloat11 is a lossless compression framework that reduces the size of LLMs and Diffusion Models by approximately 30% while preserving bit-for-bit identical outputs to the original model. It enables efficient GPU inference on resource-constrained hardware without sacrificing accuracy.

## 🚀 Key Features

* **Lossless Compression**: Achieves \~30% model size reduction with outputs identical to the original BFloat16 models.
* **GPU-Efficient**: All decompression is handled on-GPU, eliminating CPU overhead and host-device data transfers.
* **Scalable Performance**: Decompression overhead remains constant per forward pass and is independent of batch size.
* **Broad Model Support**: Compatible with various models, including Qwen3, Gemma3, Llama3, Phi4, Wan2.1, FLUX.1, and BAGEL.

## 🛠 Installation

Ensure you have a CUDA-compatible GPU and PyTorch installed.

```bash
# For CUDA 12
pip install -U dfloat11[cuda12]

# For CUDA 11
pip install -U dfloat11[cuda11]
```

## 🧪 Quick Start

For example usage, refer to the [examples directory](https://github.com/LeanModels/DFloat11/tree/master/examples) in the GitHub repository.

## 📄 Learn More

* **Paper**: [70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float](https://arxiv.org/abs/2504.11651)
* **GitHub Repository**: [LeanModels/DFloat11](https://github.com/LeanModels/DFloat11)
* **Hugging Face Models**: [DFloat11 on Hugging Face](https://huggingface.co/DFloat11)