How to deploy gpt-oss-120b and gpt-oss-20b chat apps in a few clicks pic.twitter.com/gi2cw5SvIu
— AK (@_akhaliq) 5 août 2025
How to deploy gpt-oss-120b and gpt-oss-20b chat apps in a few clicks
By
–
How to deploy gpt-oss-120b and gpt-oss-20b chat apps in a few clicks pic.twitter.com/gi2cw5SvIu
— AK (@_akhaliq) 5 août 2025
How to deploy gpt-oss-120b and gpt-oss-20b chat apps in a few clicks

By
–
Equip your agent with different subsets of tools throughout a run with dynamic tool selection in LangGraph!
By
–
Partnering with @huggingface has been incredible. We also worked with @ollama
, @lmstudio
, @vllm_project
, so you can run models locally with your favorite tool on day one, and with many cloud and hardware partners so you can deploy it efficiently anywhere.
By
–
Looks like @lmstudio were a launch partner and have their own official GGUF release up here:
By
–
Yeah I'm hoping someone comes up with a Mac-friendly (maybe MLX?) quantized version with a robust tool calling prompt template soon

By
–
I tried out the first 20B GGUF version I spotted in Hugging Face using LM Studio, which complained about the prompt template. I managed to get a pelican out of it though! https://
huggingface.co/gabriellarson/
gpt-oss-20b-GGUF
…
By
–
Aparte lo tendréis disponible en los lugares habituales para descargar (Ollama, LMStudio, HuggingFace, etc)

By
–
Si queréis testear estos modelos antes de descargarlos, tenéis una demo disponible a continuación https://
gpt-oss.com
By
–
Both gpt-oss models are free to download on Hugging Face, with native MXFP4 quantization built in for efficient deployment. Full list of day-one support is available on our blog.
By
–
Claude Opus 4.1 is available in Cursor! Let us know what you think.