Neural Network Compression Framework (NNCF)

Neural Network Compression Framework (NNCF) provides a suite of post-training and training-time algorithms for optimizing inference of neural networks in OpenVINO™ with a minimal accuracy drop.

NNCF is designed to work with models from PyTorch, TorchFX, ONNX and OpenVINO™.

NNCF provides samples that demonstrate the usage of compression algorithms for different use cases and models. See compression results achievable with the NNCF-powered samples on the NNCF Model Zoo page.

The framework is organized as a Python* package that can be built and used in a standalone mode. The framework architecture is unified to make it easy to add different compression algorithms for both PyTorch deep learning frameworks.

For more information about NNCF, see:

Key Features
Installation
Third-party integration

Key Features

Post-Training Compression Algorithms

Compression algorithm	OpenVINO	PyTorch	TorchFX	ONNX
Post-Training Quantization	Supported	Supported	Experimental	Supported
Weights Compression	Supported	Supported	Experimental	Supported
Activation Sparsity	Not supported	Experimental	Not supported	Not supported

Training-Time Compression Algorithms

Compression algorithm	PyTorch
Quantization Aware Training	Supported
Weight-Only Quantization Aware Training with LoRA and NLS	Supported
Pruning	Supported

Automatic, configurable model graph transformation to obtain the compressed model.
Common interface for compression methods.
GPU-accelerated layers for faster compressed model fine-tuning.
Distributed training support.
Git patch for prominent third-party repository (huggingface-transformers) demonstrating the process of integrating NNCF into custom training pipelines.
Exporting PyTorch compressed models to ONNX* checkpoints compressed models to SavedModel or Frozen Graph format, ready to use with OpenVINO™ toolkit.

Installation Guide

For detailed installation instructions, refer to the Installation guide.

NNCF can be installed as a regular PyPI package via pip:

pip install nncf

NNCF is also available via conda:

conda install -c conda-forge nncf

System requirements of NNCF correspond to the used backend. System requirements for each backend and the matrix of corresponding versions can be found in installation.md.

Third-party Repository Integration

NNCF may be easily integrated into training/evaluation pipelines of third-party repositories.

Used by

HuggingFace Optimum Intel

NNCF is used as a compression backend within the renowned transformers repository in HuggingFace Optimum Intel. For instance, the command below exports the Llama-3.2-3B-Instruct model to OpenVINO format with INT4-quantized weights:
```
optimum-cli export openvino -m meta-llama/Llama-3.2-3B-Instruct --weight-format int4 ./Llama-3.2-3B-Instruct-int4
```
Ultralytics

NNCF is integrated into the Intel OpenVINO export pipeline, enabling quantization for the exported models.
ExecuTorch

NNCF is used as primary quantization framework for the ExecuTorch OpenVINO integration.
torch.compile

NNCF is used as primary quantization framework for the torch.compile OpenVINO integration.
OpenVINO Training Extensions

NNCF is integrated into OpenVINO Training Extensions as a model optimization backend. You can train, optimize, and export new models based on available model templates as well as run the exported models with OpenVINO.
Microsoft Olive

NNCF is used to quantize OpenVINO IR and ONNX models for the OpenVINO integration.

NNCF Compressed Model Zoo

List of models and compression results for them can be found at our NNCF Model Zoo page.

Citing

@article{kozlov2020neural,
    title =   {Neural network compression framework for fast model inference},
    author =  {Kozlov, Alexander and Lazarevich, Ivan and Shamporov, Vasily and Lyalyushkin, Nikolay and Gorbachev, Yury},
    journal = {arXiv preprint arXiv:2002.08679},
    year =    {2020}
}

Telemetry

NNCF as part of the OpenVINO™ toolkit collects anonymous usage data for the purpose of improving OpenVINO™ tools. You can opt-out at any time by running the following command in the Python environment where you have NNCF installed:

opt_in_out --opt_out

More information available on OpenVINO telemetry.

Release files for nncf 3.4.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for nncf 3.4.0
File	Size	Uploaded
nncf-3.4.0.tar.gz	559.3 kB	Sep 17, 2026	Details

Built distribution (wheel)

Table of built distributions (wheels) for nncf 3.4.0
File	Interpreter	ABI	Platform	Reset
nncf-3.4.0-py3-none-any.whl 797.3 kB Sep 17, 2026	Python 3	none	any	Details

Total release size: 1.4 MB

Release files / nncf-3.4.0.tar.gz

Download URL	nncf-3.4.0.tar.gz
Size	559.3 kB
Tags	Source
SHA-256 checksum How to use checksums	`40b835e275b091197b853344de98ebe1026b58acfb83ffe69b9a0be305371d66`
BLAKE2b-256 checksum How to use checksums	`fa1cd48fd3a520ec492867fb59679b30bf1e39468b73a7e24184e36f0dc3b8de`
Upload date	Sep 17, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.12.14`

Release files / nncf-3.4.0-py3-none-any.whl

Download URL	nncf-3.4.0-py3-none-any.whl
Size	797.3 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`bc1b8b2fec7ac76462d8156df8c1b415e95ff3fc453e494787c64ea413f6663c`
BLAKE2b-256 checksum How to use checksums	`168b4c1f567ae289c36e48557ec9889c0d3b153e05cf8b043e342939e494a5d9`
Upload date	Sep 17, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/7.0.0 CPython/3.12.14`