Optimum

license

Apache-2.0(OSI)

source

public

core features withheld

no

The library is licensed under Apache-2.0 and its source is public. The README describes the whole library with no paid, enterprise or hosted tier beside it, so nothing in the core is withheld.

• https://github.com/huggingface/optimum/blob/main/LICENSE recorded 2026-08-13

  LICENSE file is the verbatim Apache License Version 2.0 text

• https://pypi.org/pypi/optimum/json recorded 2026-09-29

  PyPI metadata for optimum lists the classifier "License :: OSI Approved :: Apache Software License", and the embedded README opens with "Licensed under the Apache License, Version 2.0". It gives the install route "python -m pip install git+https://github.com/huggingface/optimum.git", so the source is public. The README describes the whole library, "Optimum is an extension of Transformers", with pip extras per accelerator and no paid tier. Searched the README for paid, enterprise, license key, self-host and open source: none.

Adoption is measured by PyPI downloads of the optimum package.

• https://pypistats.org/api/packages/optimum/recent recorded 2026-08-13

  last_month downloads = 1,919,623 for optimum

Optimum covers model export, quantization and accelerated training and inference across ONNX Runtime, OpenVINO, ExecuTorch, Intel Gaudi, AWS Trainium and Inferentia, and TensorRT-LLM. It is an extension of Transformers and depends on it, so it sits a step below Transformers.

• https://github.com/huggingface/optimum recorded 2026-08-13

  README still describes hardware-targeted optimization, export and quantization across ONNX Runtime, OpenVINO, Gaudi, Trainium/Inferentia and TensorRT-LLM

• https://huggingface.co/docs/optimum/index recorded 2026-09-29

  The Optimum docs home says "Optimum is an extension of" Transformers that provides "a set of performance optimization tools to train and run models on targeted hardware with maximum efficiency."

• https://pypi.org/pypi/optimum/json recorded 2026-09-29

  The PyPI README says "Optimum provides multiple tools to export and run optimized models on various ecosystems", listing ONNX Runtime, OpenVINO, ExecuTorch, Intel Gaudi, AWS Inferentia and NVIDIA TensorRT-LLM, and "Optimum provides wrappers around the original Transformers" Trainer for training on Gaudi and Trainium.