# openai/gpt-oss-20b

> Source: <https://huggingbay.xyz/artifact/hf-model-openai-gpt-oss-20b>
> Published: 2026-07-03 04:19:42+00:00

# openai/gpt-oss-20b

openai/gpt-oss-20b: Model from Hugging Face: openai/gpt-oss-20b License: apache-2.0. 6 Hugging Bay hosted files. Scan: passed.

- License
- apache-2.0
- Size
- 38.5 GB
- Demand
- 7.0M upstream downloads
- Trust
- Verified 28/100
- Trusted download
- Verified hosted files
- Run fit
- Large hardware fit: Multi-GPU, high-RAM machine, or hosted inference
- Files
- 6 hosted / 18 total
- Scan status
- passed
- Hosting status
- partial
- Upstream
- openai/gpt-oss-20b
- Declared license
- apache-2.0
- Pipeline
- text-generation
- Library
- transformers
- Task categories
- text-generation

## About this artifact

External Hugging Face catalog record for openai/gpt-oss-20b. Popularity signal at import: 7,011,565 downloads and 4,753 likes. Files are listed for discovery and verification context, but this Hugging Bay pilot has not mirrored or rescanned the remote blobs. Use the upstream Hugging Face links for download until an explicit mirror job is approved.

## Trusted download

Verified hosted files. Hugging Bay hosts reviewed files with SHA-256 hashes and a signed manifest.

- Hosted files
- 6 of 18
- Reviewed peer-assisted fallbacks
- 0
- Download plan
[Download-plan JSON](/api/artifacts/hf-model-openai-gpt-oss-20b/download-plan)- Trust bundle
[Trust-bundle JSON](/api/trust-bundles/hf-model-openai-gpt-oss-20b)- Review summary
[Review-summary JSON](/api/artifacts/hf-model-openai-gpt-oss-20b/review-summary)- Distribution
[Reviewed peer-fallback JSON](/api/artifacts/hf-model-openai-gpt-oss-20b/distribution)

- config.json - 1.8 KB - sha256 3a2a26ded679375b7928ddeca59764df7cea83220c1961035f6d6e232659e9ce
- generation_config.json - 177 B - sha256 f9970ada892d2d1f72e3ed0a6535ccebadd11897318794ca671d8c7014c957da
- original/config.json - 376 B - sha256 317522155fc243327ee341857d0c752d0094a0817e0e9aee2890d5ad8e009e04
- special_tokens_map.json - 98 B - sha256 dd5e191d20c12d2fee1da5bae14ca1db0f5f4215300af691f23cdee97120a293
- tokenizer.json - 26.6 MB - sha256 0614fe83cadab421296e664e1f48f4261fa8fef6e03e63bb75c20f38e37d07d3
- tokenizer_config.json - 4.1 KB - sha256 9279e942392b742d633c7adbb89ebe002c98399db8926a7af5125c726f404070

## Can I run this?

Large hardware fit. Multi-GPU, high-RAM machine, or hosted inference. Use compare pages to find smaller verified alternatives or request a quantized mirror if one is not hosted yet.

- Estimated footprint
- 38.4 GB
- Suggested runners
- Transformers, vLLM
- Runtime files
- 6
- Local kit
[Local run kit](/local-kit/hf-model-openai-gpt-oss-20b)

- metal/model.bin - 12.8 GB
- model-00000-of-00002.safetensors - 4.5 GB
- model-00001-of-00002.safetensors - 4.5 GB
- model-00002-of-00002.safetensors - 3.9 GB
- model.safetensors.index.json - 35.5 KB
- original/model.safetensors - 12.8 GB

- License: pass - apache-2.0
- Provenance: pass - openai/gpt-oss-20b
- Scan: pass - passed
- Hosted files: pass - 6/18 hosted
- Signed manifest: pass - final manifest available
- Community: warn - no reviews yet
- Benchmarks: warn - no benchmark evidence

## Machine-readable card

[Open interactive artifact page](/#/artifact/hf-model-openai-gpt-oss-20b)