Hugging Face · #23

openai/gpt-oss-20b

openai/gpt-oss-20b is a 20.9B text-generation model on Hugging Face. Run locally: llama-cli -hf openai/gpt-oss-20b or ollama run hf.co/openai/gpt-oss-20b. 5,197 Hugging Face likes (#23 in this directory).

Model
https://huggingface.co/openai/gpt-oss-20b
Author
openai (org)
Likes
5,197
Downloads (30 days)
5,892,118
Task
text-generation
Library
transformers
License
apache-2.0
Parameters
20.9B
Gated
No
Created
2025-08-04
Last modified
2025-08-26
Snapshot
2026-10-29

Run it locally.

Shadowfetch Linux is a Debian testing desktop with KDE Plasma, local AI tools, and ShadowCode. ShadowCode's bundled llama.cpp runs GGUF models; you can also use llama.cpp or Ollama from the terminal.

llama.cpp

llama-cli -hf openai/gpt-oss-20b

Ollama

ollama run hf.co/openai/gpt-oss-20b

These commands work when this repo, or a GGUF quant of it, publishes GGUF weights. They do not invent a quant name. For safetensors-only repos, convert with llama.cpp or use a GGUF repo on the Hub.

ShadowCode prompt.

Paste this into ShadowCode after you open Settings › Local models.

In Settings › Local models, run openai/gpt-oss-20b only if a GGUF file is available. If the Hub repo is safetensors-only, use a GGUF quant instead of guessing a filename. Ask before downloading.

Download Shadowfetch Linux — ISO, checksum and signature.

Back to Hugging Face models · Methodology