CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.gpt-oss / gpt-oss-safeguard-20b-GGUF
From: unsloth <huggingface.co/unsloth>Newsgroups: alt.freeweights.gpt-ossSubject:

gpt-oss-safeguard-20b-GGUF

Date: 2026-11-15Commit: 8663c20Signed: 2DC28CC7B26A283B ✓

Text generation model. Gguf weights, 191 GB in all. Published by unsloth under Apache-2.0.

gpt-oss191GBgpt-oss-safeguard-20b-GGUFggufpermissive
FactsParamsnot statedSize191 GBFormatsggufTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get unsloth/gpt-oss-safeguard-20b-GGUF
# manifest sha256 5c0fe125481e… · 191 GB · 18 files
$ fw verify ./gpt-oss-safeguard-20b-GGUF unsloth/gpt-oss-safeguard-20b-GGUF
From sourceHosted (signed)unsloth/gpt-oss-safeguard-20b-GGUFLast check: 2026-11-15 05:01 UTC
Run at homeGet help

Get help: custom fine-tune or private deploy. We review your setup before we quote.

Quantized of gpt-oss-safeguard-20b.

Works with

Run14Convert1Evaluate13Scan12Apps58

Convert with

ggml
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
191 GB
Weights
11.5 GB (smallest of 16 GGUF variants)
Parameters
not stated
Formats
gguf
Task
text generation
License
Apache-2.0 (permissive)
Files
18, each with a sha256
Publisher
unsloth
Added
2026-11-15
Section
alt.freeweights.gpt-oss
Lineage

Original release from the publisher.

Base model: openai/gpt-oss-safeguard-20b

Where these bytes come from
Publisher at the pinned commit→You

Sources are tried in order. A file counts only when its size and sha256 match the manifest. Sources are checked when you ask for them, not on a timer.

Sources
BadgeHostLast checkResult
From sourcehuggingface.co2026-11-15 05:01 UTCpassed

Model card

From the publisher at commit 8663c20. Shown as plain text with links; images open at the publisher.

Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants.

https://github.com/unslothai/unsloth/ https://discord.gg/unsloth https://docs.unsloth.ai/

Image: gpt-oss-safeguard-20b

Try gpt-oss-safeguard · Guide · Model card · OpenAI blog

gpt-oss-safeguard-120b and gpt-oss-safeguard-20b are safety reasoning models built-upon gpt-oss. With these models, you can classify text content based on safety policies that you provide and perform a suite of foundational safety tasks. These models are intended for safety use cases. For other applications, we recommend using gpt-oss models.

This model gpt-oss-safeguard-20b (21B parameters with 3.6B active parameters) fits into GPUs with 16GB of VRAM. Check out gpt-oss-safeguard-120b (117B parameters with 5.1B active parameters) for the larger model.

Both models were trained on our harmony response format and should only be used with the harmony format as it will not work correctly otherwise.

Highlights#

  • Trained to reason about safety : Trained and tuned for safety reasoning to accommodate use cases like LLM input-output filtering, online content labeling and offline labeling for Trust and Safety use cases.
  • Bring your own policy: Interprets your written policy, so it generalizes across products and use cases with minimal engineering.
  • Reasoned decisions, not just scores: Gain complete access to the model’s reasoning process, facilitating easier debugging and increased trust in policy decisions. Keep in mind Raw CoT is meant for developers and safety practitioners. It’s not intended for exposure to general users or use cases outside of safety contexts.
  • Configurable reasoning effort: Easily adjust the reasoning effort (low, medium, high) based on your specific use case and latency needs.
  • Permissive Apache 2.0 license: Build freely without copyleft restrictions or patent risk—ideal for experimentation, customization, and commercial deployment.

Inference examples#

You can use gpt-oss-safeguard-120b and gpt-oss-safeguard-20b similar to gpt-oss-120b and gpt-oss-20b as described in our respective cookbooks. We’ve also provided a detailed prompting guide that provides guidelines for how to craft your policy and use it with the models.

Download the model#

To download the model weights from Hugging Face hub using similar instructions to gpt-oss-120b.

Join the ROOST Model Community#

gpt-oss-safeguard is a model partner of the Robust Open Online Safety Tools (ROOST) Model Community. The ROOST Model Community (RMC) is a group of safety practitioners exploring open source AI models to protect online spaces. As an RMC model partner, OpenAI is committed to incorporating user feedback and jointly iterating on future releases in pursuit of open safety. Visit the RMC GitHub repo to learn more about this partnership and how to get involved.

Resources#

Files

18 files · 191 GBWeights 11.5 GB (smallest of 16 GGUF variants). Sizes and sha256 from the signed manifest.
Hide all 18 files with their sha256
FileSizesha256
.gitattributes2.57 KB7e9363c9c09b3d819c2bd251b7679ed9fd4386c4d749cc05d88ec5189b50726c
README.md4.86 KB1fc3859a87459d35f809dea8b92d838a167f2802340108c90b640233b98bf8b5
gpt-oss-safeguard-20b-F16.gguf13.8 GB1515212172e3acbf6ab89a8ed3467fbedeac27c29ce28649de1509662fbe6475
gpt-oss-safeguard-20b-Q2_K.gguf11.5 GB5e7e15bfa009d5b0e940a0d31807f58cbccb4e3dee3e6e4ea072cf36df9c44b4
gpt-oss-safeguard-20b-Q2_K_L.gguf11.8 GB8ece1bd3a20e6c04e32dd7efd40f70a95d8d1ba70d159c1176936fb9a3a69790
gpt-oss-safeguard-20b-Q3_K_M.gguf11.5 GBa5a9f7caa84c7eeb32c785c9716d5b9473e5ae8cd96cdc2dcee486c4f6f2e1db
gpt-oss-safeguard-20b-Q3_K_S.gguf11.5 GBaddb58f117cc8255340792ed7a12fa38fef5c7dd85585a675dc14cdb28dd5ec1
gpt-oss-safeguard-20b-Q4_0.gguf11.5 GB0a9471951944c91c2286fc202cb7ccbd849bc89f274304f50d37b59ceec3a5a9
gpt-oss-safeguard-20b-Q4_1.gguf11.6 GBfe1391999c69c93a580cf5ab4116b06f5e2d6826ec092349ab16c9d4f5625039
gpt-oss-safeguard-20b-Q4_K_M.gguf11.6 GB7c70a6d00294bafb0a118d4deb1697ee8cf0cef8e65dc5dedcc25cbbe4699bad
gpt-oss-safeguard-20b-Q4_K_S.gguf11.6 GBbfd164d855b599d3cc19581d12bd06370f5f96e382aa41df39363d5ae7c8021c
gpt-oss-safeguard-20b-Q5_K_M.gguf11.7 GB744eeac466eb03e1966f5cd3d0c55d068653d9fc24b507fae6672b71ce14cabf
gpt-oss-safeguard-20b-Q5_K_S.gguf11.7 GBdd2d7ded5df90d39f58dd3487d382648c8946e0fdfda99e3a3787acb5670634b
gpt-oss-safeguard-20b-Q6_K.gguf12.0 GBdc6dbe1445cd1628ffc7a84ee4c7c6fb4d8082962dee8e193c390efab950df1d
gpt-oss-safeguard-20b-Q8_0.gguf12.1 GBd78461375a173961e2f1f1c809706e478beca06ddb2eb74e2493b323ffa3a36d
gpt-oss-safeguard-20b-UD-Q4_K_XL.gguf11.9 GB18f85151a41f9b1abed10ff8875b07cbe259dce58b7ae19c77b1727d2c4ecf71
gpt-oss-safeguard-20b-UD-Q6_K_XL.gguf12.0 GBdc6dbe1445cd1628ffc7a84ee4c7c6fb4d8082962dee8e193c390efab950df1d
gpt-oss-safeguard-20b-UD-Q8_K_XL.gguf13.2 GB51011b84131acd4a78e786d70d6db4c0ff1e4b179f49db3c12e6204b71a079ab
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
8663c2039e pinned now2026-11-15 05:01 UTC18 files · 191 GB

Use it

$ fw get unsloth/gpt-oss-safeguard-20b-GGUF
# manifest sha256 5c0fe125481e… · 191 GB · 18 files
$ fw verify ./gpt-oss-safeguard-20b-GGUF unsloth/gpt-oss-safeguard-20b-GGUF
fw.pyChecks the signature and every sha256, tries each source in order, resumes.
$ python3 fw.py get https://freeweights.allternit.com/manifests/unsloth/gpt-oss-safeguard-20b-GGUF.json --dir ./gpt-oss-safeguard-20b-GGUF $ python3 fw.py verify ./gpt-oss-safeguard-20b-GGUF ./unsloth__gpt-oss-safeguard-20b-GGUF.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download unsloth/gpt-oss-safeguard-20b-GGUF --revision 8663c2039e7dab29d93bdf6d1827c9ce882721da --local-dir ./gpt-oss-safeguard-20b-GGUF
llama.cppDownload one GGUF variant (gpt-oss-safeguard-20b-Q3_K_S, 11.5 GB), then serve it.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download unsloth/gpt-oss-safeguard-20b-GGUF --include "gpt-oss-safeguard-20b-Q3_K_S*" --local-dir ./gpt-oss-safeguard-20b-GGUF $ llama-server -m ./gpt-oss-safeguard-20b-GGUF/gpt-oss-safeguard-20b-Q3_K_S.gguf
OllamaMake an Ollama model from the downloaded file.
$ printf 'FROM ./gpt-oss-safeguard-20b-GGUF/gpt-oss-safeguard-20b-Q3_K_S.gguf\n' > Modelfile $ ollama create gpt-oss-safeguard-20b-gguf -f Modelfile
Run at home

License

Name
Apache License 2.0
Id
Apache-2.0
Class
Permissive
Redistribution
yes
Listing
Hosted (signed)
Decided
License as declared by the publisher. No person read it. 2026-11-15
Text in
README.md
Text sha256
1fc3859a87459d35f809dea8b92d838a167f2802340108c90b640233b98bf8b5
Terms gate
No extra terms beyond the license.

Read the license text

Licenses are checked against the license table. A custom license passes only after a person reads it.

Provenance

From: unsloth <huggingface.co/unsloth>Newsgroups: alt.freeweights.gpt-ossSubject: gpt-oss-safeguard-20b-GGUFDate: 2026-11-15Commit: 8663c20Signed: 2DC28CC7B26A283B ✓
Upstream
unsloth/gpt-oss-safeguard-20b-GGUF
Pinned commit
8663c2039e7dab29d93bdf6d1827c9ce882721da
Manifest
gpt-oss-safeguard-20b-GGUF.json · .minisig
Manifest sha256
5c0fe125481ef584d78021a8589c53b11772c2d08fb86dbabfd4e611c25c2374
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:01 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/unsloth/gpt-oss-safeguard-20b-GGUF.json $ curl -O https://freeweights.allternit.com/manifests/unsloth/gpt-oss-safeguard-20b-GGUF.json.minisig $ minisign -Vm gpt-oss-safeguard-20b-GGUF.json -P RWQ7KGqyx4zCLXtUFOqvfv8L3g+8fpKJ1FsuxPyOYMF+4KufbUxKq1Oq $ shasum -a 256 <file> # compare with the Files tab

A manifest whose signature fails must be rejected. A file whose size or sha256 does not match must be discarded. Verify a download

Model tree

Parent

openai/gpt-oss-safeguard-20b · this model is a quantization of it

No model in the catalog names this one as its parent.

Get it
Download
$ HF_ENDPOINT=https://freeweights.allternit.com hf download unsloth/gpt-oss-safeguard-20b-GGUF
Open in Freeweights Studio

Pull, verify and run it in the Allternit app on Desktop, web or phone.

Signed manifest
minisign, key 2DC28CC7B26A283B. gpt-oss-safeguard-20b-GGUF.json. Provenance. Takedown history: none.
Source
huggingface.co/unsloth/gpt-oss-safeguard-20b-GGUF

Related models

All of alt.freeweights.gpt-oss →
From: unsloth <huggingface.co/unsloth>Subject: gpt-oss-120b
From: mlx-community <huggingface.co/mlx-community>Subject: gpt-oss-120b-4bit
From: unsloth <huggingface.co/unsloth>Subject: gpt-oss-120b-BF16
From: lmstudio-community <huggingface.co/lmstudio-community>Subject: gpt-oss-120b-GGUF
From: unsloth <huggingface.co/unsloth>Subject: gpt-oss-120b-GGUF
From: lmstudio-community <huggingface.co/lmstudio-community>Subject: gpt-oss-120b-MLX-8bit