neural-compressor
SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime
Apply advanced techniques to reduce the size of machine learning models for better performance on popular frameworks.
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 anytimeSOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime
neural-compressor has 2.7k stars on GitHub. It has been forked 320 times. neural-compressor is written mainly in Python. It has been in active development since 2020. neural-compressor is available under the Apache-2.0 license. Its main topics are auto-tuning, awq, fp4, gptq.
What is neural-compressor?
SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime
Is neural-compressor open source?
neural-compressor is an open-source project. It is released under the Apache-2.0 license.
Is neural-compressor free?
Yes. neural-compressor is free and open source — you can use, modify and self-host it.
What license does neural-compressor use?
neural-compressor is available under the Apache-2.0 license.
What language is neural-compressor written in?
neural-compressor is written mainly in Python.
Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.
[](https://olud.ai/project/intel-neural-compressor.html)
Measured from GitHub topics shared by both projects, weighted by how rare each topic is.