gpt-oss

<img alt="gpt-oss-120" src="./docs/gpt-oss.svg">
<p align="center">
  <a href="https://gpt-oss.com"><strong>Try gpt-oss</strong></a> ·
  <a href="https://cookbook.openai.com/topic/gpt-oss"><strong>Guides</strong></a> ·
  <a href="https://arxiv.org/abs/2508.10925"><strong>Model card</strong></a> ·
  <a href="https://openai.com/index/introducing-gpt-oss/"><strong>OpenAI blog</strong></a>
</p>
<p align="center">
  <strong>Download <a href="https://huggingface.co/openai/gpt-oss-120b">gpt-oss-120b</a> and <a href="https://huggingface.co/openai/gpt-oss-20b">gpt-oss-20b</a> on Hugging Face</strong>
</p>

<br>

Welcome to the gpt-oss series, [OpenAI's open-weight models](https://openai.com/open-models/) designed for powerful reasoning, agentic tasks, and versatile developer use cases.

We're releasing two flavors of these open models:

- `gpt-oss-120b` — for production, general purpose, high reasoning use cases that fit into a single 80GB GPU (like NVIDIA H100 or AMD MI300X) (117B parameters with 5.1B active parameters)
- `gpt-oss-20b` — for lower latency, and local or specialized use cases (21B parameters with 3.6B active parameters)

Both models were trained using our [harmony response format][harmony] and should only be used with this format; otherwise, they will not work correctly.

## Table of Contents
- [Highlights](#highlights)
- [Inference examples](#inference-examples)
- [About this repository](#about-this-repository)
- [Setup](#setup)
- [Download the model](#download-the-model)
- [Reference PyTorch implementation](#reference-pytorch-implementation)
- [Reference Triton implementation (single GPU)](#reference-triton-implementation-single-gpu)
- [Reference Metal implementation](#reference-metal-implementation)
- [Harmony format & tools](#harmony-format--tools)
- [Clients](#clients)
- [Tools](#tools)
- [Other details](#other-details)
- [Contributing](#contributing)

### Highlights

- **Permissive Apache 2.0 license:** Build freely without copyleft restrictions or patent risk—ideal for experimentation, customization, and commercial deployment.
- **Configurable reasoning effort:** Easily adjust the reasoning effort (low, medium, high) based on your specific use case and latency needs.
- **Full chain-of-thought:** Provides complete access to the model's reasoning process, facilitating easier debugging and greater trust in outputs. This information is not intended to be shown to end users.
- **Fine-tunable:** Fully customize models to your specific use case through parameter fine-tuning.
- **Agentic capabilities:** Use the models' native capabilities for function calling, [web browsing](#browser), [Python code execution](#python), and Structured Outputs.
- **MXFP4 quantization:** The models were post-trained with MXFP4 quantization of the MoE weights, making `gpt-oss-120b` run on a single 80GB GPU (like NVIDIA H100 or AMD MI300X) and the `gpt-oss-20b` model run within 16GB of memory. All evals were performed with the same MXFP4 quantization.

### Infer