# OpenAI gpt-oss

DevFeed: [OpenAI gpt-oss](<https://devfeed.tech/articles/openai-gpt-oss-83374.md>)

Original publisher: [Read original article](<https://ollama.com/blog/gpt-oss>)

Published: 2025-08-05T00:00:00Z

Content type: release

Language: en

Sources: [Ollama](<https://devfeed.tech/sources/ollama.md>)

Topics: [gpt-oss](<https://devfeed.tech/topics/gpt-oss.md>), [Ollama](<https://devfeed.tech/topics/ollama.md>), [quantization](<https://devfeed.tech/topics/quantization.md>)

Tags: [apache-2-0](<https://devfeed.tech/tags/apache-2-0.md>), [browsing](<https://devfeed.tech/tags/browsing.md>), [fine-tuning](<https://devfeed.tech/tags/fine-tuning.md>), [function-calling](<https://devfeed.tech/tags/function-calling.md>), [gpt-oss](<https://devfeed.tech/tags/gpt-oss.md>), [gpu](<https://devfeed.tech/tags/gpu.md>), [mixture-of-experts-moe](<https://devfeed.tech/tags/mixture-of-experts-moe.md>), [mxfp4](<https://devfeed.tech/tags/mxfp4.md>), [ollama](<https://devfeed.tech/tags/ollama.md>), [open-weight-models](<https://devfeed.tech/tags/open-weight-models.md>), [openai](<https://devfeed.tech/tags/openai.md>), [performance](<https://devfeed.tech/tags/performance.md>)

## AI overview

Ollama's release introduces OpenAI's gpt-oss 20B and 120B open-weight models for local chat, reasoning, agentic tasks, and developer use cases. It highlights function calling, web browsing, Python tool calls, structured outputs, configurable reasoning effort, fine-tuning, and the Apache 2.0 license. The post also describes MXFP4 quantization, memory requirements, native support in Ollama, and a collaboration with NVIDIA to improve performance on GeForce RTX and RTX PRO GPUs.

## Source excerpt

Ollama partners with OpenAI to bring gpt-oss to Ollama and its community.