FreeAIRepo
Training & fine-tuning

intel/neural-compressor

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

Apache-2.0Runs on MacPython
Stars
2.7k
Forks
330
Open issues
3
Last push
1d ago

About neural-compressor

neural-compressor is a free, open-source machine learning tool by intel, written mainly in Python. SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime. It has 2.7k GitHub stars and 330 forks, and was last updated 1d ago. It's released under the Apache-2.0 license, a standard open-source license. According to the project, it works on macOS.

License
Apache-2.0
Language
Python
Stars
2,723
Last update
1d ago
Runs on Mac
Yes (as stated by the project)
GPU
Not stated
Paid API key
Not stated
Self-hostable
Yes

Similar free tools

All Training & fine-tuning tools →

neural-compressor FAQ

Is neural-compressor free?

Yes. neural-compressor is open source and free to use. It's released under the Apache-2.0 license, a standard open-source license.

Does neural-compressor run on a Mac?

Yes. According to the project, neural-compressor works on macOS.

Does neural-compressor need a GPU?

The project doesn't state hardware needs. AI models generally run much faster with a GPU.

Is neural-compressor still maintained?

Yes. It was last updated 1d ago and has 3 open issues on GitHub.

What are alternatives to neural-compressor?

Similar free, open-source tools include LlamaFactory, pytorch-image-models, align-anything, DoRA.

Related topics