DFloat11
DFloat11 [NeurIPS '25]: Lossless Compression of LLMs and DiTs for Efficient GPU Inference
Reduce the size of large AI models by 30% while keeping their outputs unchanged for faster processing.
Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.
Get an email alert on its next release or when it starts trending — never miss the moment.
Free · no card · unsubscribe anytimeDFloat11 [NeurIPS '25]: Lossless Compression of LLMs and DiTs for Efficient GPU Inference
DFloat11 has 642 stars on GitHub. It has been forked 38 times. DFloat11 is written mainly in Python. It has been in active development since 2025. DFloat11 is available under the Apache-2.0 license. Its main topics are compression, diffusion-models, gpu, llm.
What is DFloat11?
DFloat11 [NeurIPS '25]: Lossless Compression of LLMs and DiTs for Efficient GPU Inference
Is DFloat11 open source?
DFloat11 is an open-source project. It is released under the Apache-2.0 license.
Is DFloat11 free?
Yes. DFloat11 is free and open source — you can use, modify and self-host it.
What license does DFloat11 use?
DFloat11 is available under the Apache-2.0 license.
What language is DFloat11 written in?
DFloat11 is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/leanmodels-dfloat11.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.