# gpt-oss

- Page: https://shared.btbytes.com/p/gpt-oss
- Date: 2025-08-20

[llama.cpp guide: running gpt-oss with llama.cpp](https://simonwillison.net/2025/Aug/19/gpt-oss-with-llama-cpp/)

```
brew install llama.cpp
llama-server -hf ggml-org/gpt-oss-20b-GGUF \
  --ctx-size 0 --jinja -ub 2048 -b 2048 -ngl 99 -fa
```

This downloads a 12GB model file from [ggml-org/gpt-oss-20b-GGUF](https://huggingface.co/ggml-org/gpt-oss-20b-GGUF/tree/main) on Hugging Face, stores it in `~/Library/Caches/llama.cpp/` and starts it running on port 8080.

You can then visit this URL to start interacting with the model: <http://localhost:8080/>