openai/gpt-oss-120b

The openai/gpt-oss-120b is a 120 billion parameter open-weight model from OpenAI, designed for powerful reasoning and agentic tasks. It features configurable reasoning effort and full chain-of-thought access, making it suitable for complex problem-solving. Optimized for production use cases, it can run on a single 80GB GPU due to MXFP4 quantization. This model excels in developer use cases including function calling, web browsing, and Python code execution.