gpt-oss:20b-cloud

Upstream reference: gpt-oss-20b

Publisher: OpenAI

OpenAI documents this open-weight text reasoning model with configurable reasoning effort and a mixture-of-experts parameter layout.

Publisher-described context, separate from Sigma5C observations and recorded catalog statistics.

Published upstream specifications

Total parameters

21 billion Source

Active parameters

3.6 billion Source

Published context

131,072 tokens Source

Upstream license label

Apache-2.0 Source

Input and output

Text Source

Publisher-described uses

• Text generation, reasoning and tool-oriented applications. Source

Reference limitations

• Tool actions require a surrounding application; the cloud suffix does not identify a deployed digest or current service availability. Source

A recorded tag and an upstream card association do not verify the deployed checkpoint, quantization, configured context or current hosted availability.

Publisher sources

• gpt-oss-20b official documentation — OpenAI. Checked 2026-11-02.

Links

Recorded references do not establish downloadable weights, licensing or current availability.

• OpenAI — official site
• Ollama
• Provider page
• Hugging Face

Where gpt-oss:20b-cloud comes from

Named in 4 observation pages

• 14B-32B local models — all 47 · V1
• 31 cloud models × 3 wrappers on the same audit · V1
• 3B-7B local models — all 53 · V1
• Cloud Models — three-judge autoresearch observation set · V1