CatalogWantedMirrorsLedgerOperating StatementDocsStudio statusCard system
alt.freeweights.gpt-oss / gpt-oss-safeguard-120b-GGUF
From: unsloth <huggingface.co/unsloth>Newsgroups: alt.freeweights.gpt-ossSubject:

gpt-oss-safeguard-120b-GGUF

Date: 2026-11-15Commit: 9a41d61Signed: 2DC28CC7B26A283B ✓

Text generation model. Gguf weights, 945 GB in all. Published by unsloth under Apache-2.0.

gpt-oss945GBgpt-oss-safeguard-120b-GGUFggufpermissive
FactsParamsnot statedSize945 GBFormatsggufTasktext generationLicenseApache-2.0From sourcepermissive
$ fw get unsloth/gpt-oss-safeguard-120b-GGUF
# manifest sha256 b0a3f8e22e6c… · 945 GB · 32 files
$ fw verify ./gpt-oss-safeguard-120b-GGUF unsloth/gpt-oss-safeguard-120b-GGUF
From sourceHosted (signed)unsloth/gpt-oss-safeguard-120b-GGUFLast check: 2026-11-15 05:11 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-120b.

Works with

Run14Convert1Evaluate13Scan12Apps58

Convert with

ggml
OverviewModel cardFilesUse itLicenseProvenanceModel tree

Overview

Size
945 GB
Weights
62.6 GB (smallest of 15 GGUF variants)
Parameters
not stated
Formats
gguf
Task
text generation
License
Apache-2.0 (permissive)
Files
32, 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-120b

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 05:11 UTCpassed

Model card

From the publisher at commit 9a41d61. 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-120b

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-120b fits into a single H100 GPU (117B parameters with 5.1B active parameters). Check out gpt-oss-safeguard-20b for lower latency (21B parameters with 3.6B active parameters).

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

32 files · 945 GBWeights 62.6 GB (smallest of 15 GGUF variants). Sizes and sha256 from the signed manifest.
Show all 32 files with their sha256
FileSizesha256
.gitattributes3.59 KBa49cb19ad98e3bf09fe50087eef3fefe3933e710c613a0aa473ee89f0123dab8
Q2_K/gpt-oss-safeguard-120b-Q2_K-00001-of-00002.gguf49.5 GB946a4374395f431098391cf36b7837e96c883dc68f4226be47277d2ffdc54297
Q2_K/gpt-oss-safeguard-120b-Q2_K-00002-of-00002.gguf13.1 GB6108b489725c17fe8ecf55c79f63360f6b2898bb7365b6a714cb473884ca1697
Q2_K_L/gpt-oss-safeguard-120b-Q2_K_L-00001-of-00002.gguf49.7 GBd4ffef8f5b750386d90249f26182f3e3f0165adf7b891df7b4cf659536501e8d
Q2_K_L/gpt-oss-safeguard-120b-Q2_K_L-00002-of-00002.gguf13.1 GB6108b489725c17fe8ecf55c79f63360f6b2898bb7365b6a714cb473884ca1697
Q3_K_M/gpt-oss-safeguard-120b-Q3_K_M-00001-of-00002.gguf49.5 GB53755c114b6d416408e7b39112e6e80aa86bf19bb5f20bf596ad2d7731791a26
Q3_K_M/gpt-oss-safeguard-120b-Q3_K_M-00002-of-00002.gguf13.1 GB4097c09922e836eeefbe339909a3e9e35aca33811dfbfa017f1ad8e9bf5e6297
Q3_K_S/gpt-oss-safeguard-120b-Q3_K_S-00001-of-00002.gguf49.5 GB9ed9442cd89554edc5ef14b23779c0c720875de35af5ddaf81e989a83cfa6a89
Q3_K_S/gpt-oss-safeguard-120b-Q3_K_S-00002-of-00002.gguf13.1 GBc81b705e6d48a9061ffecd926223fbb2b03d5b42620fa0d557595dc0bcee1f7f
Q4_0/gpt-oss-safeguard-120b-Q4_0-00001-of-00002.gguf49.5 GBdd53041430abd662ae6e007ee4629c6c0d1773dbbe0474935b175189606084b0
Q4_0/gpt-oss-safeguard-120b-Q4_0-00002-of-00002.gguf13.1 GB8c94af83cd8272fd5003c4c0e9f577c7aaca3d83cc2c505e86d0c6480052ad4d
Q4_1/gpt-oss-safeguard-120b-Q4_1-00001-of-00002.gguf49.6 GB92e2d9853e8b35f0a776d77624f5572f1cca011926200cfb4e44be54d2707a67
Q4_1/gpt-oss-safeguard-120b-Q4_1-00002-of-00002.gguf13.1 GB8f3f92359031fe90681922544f8168d8fffb353980859974342103cd0aedf0b2
Q4_K_M/gpt-oss-safeguard-120b-Q4_K_M-00001-of-00002.gguf49.6 GBaf0cebe6288342e1636424057b7ce3967a06ec6f83d2fa85e0ef938a186d404b
Q4_K_M/gpt-oss-safeguard-120b-Q4_K_M-00002-of-00002.gguf13.1 GBf7588f437ada27d5ad02c994dba5c149ecd4bde2b36113fce5b07a96379a8e01
Q4_K_S/gpt-oss-safeguard-120b-Q4_K_S-00001-of-00002.gguf49.6 GBa741eb85c3512a7631aad4c7249d517f68dddbf2d80a15eb15698e572bd2449d
Q4_K_S/gpt-oss-safeguard-120b-Q4_K_S-00002-of-00002.gguf13.1 GB386f0df133ef0ea362a0e5ba6f3838324dde22a567032b83f3c29771cbcf7146
Q5_K_M/gpt-oss-safeguard-120b-Q5_K_M-00001-of-00002.gguf49.7 GB44cf4fa7a54c48aa77b926f6706f0261b009402477f9c5867107029d18f9936f
Q5_K_M/gpt-oss-safeguard-120b-Q5_K_M-00002-of-00002.gguf13.2 GBfaeb2c96d7da940df86dd5ef76a290fcef8ac9032d9b942107f468423ad0d1e3
Q5_K_S/gpt-oss-safeguard-120b-Q5_K_S-00001-of-00002.gguf49.7 GBdc03e2c48c8be1079b580d6503641b27e7fc371da47b7a7fd81e1495a2e7437d
Q5_K_S/gpt-oss-safeguard-120b-Q5_K_S-00002-of-00002.gguf13.2 GB955ecb674c81e52fd75d2c318f0ed9b265ce1f0375e692752982cbd55d08d6c1
Q6_K/gpt-oss-safeguard-120b-Q6_K-00001-of-00002.gguf49.5 GB3a09c2a0c2ab92e136c356a8c451b746c10eed46ba4eb45dd8e5b5e404b4aa64
Q6_K/gpt-oss-safeguard-120b-Q6_K-00002-of-00002.gguf13.8 GBb1114cc9554131c5ed701f0c229b2e1337c572f918c9119015a48ad302109052
Q8_0/gpt-oss-safeguard-120b-Q8_0-00001-of-00002.gguf49.6 GB96d67413ae81aed38c57fb8a0a1de0f20bc6f79b587414b7ec7e4fa02947409c
Q8_0/gpt-oss-safeguard-120b-Q8_0-00002-of-00002.gguf13.8 GB43477d2e205a7e589663afdaa31944d13eb9f8248988e0730837da320c6a2d13
README.md4.85 KBe355f169ad310a40fd2feb5f90e9997626d6953f41b9a2593e926da5b64eb3cc
UD-Q4_K_XL/gpt-oss-safeguard-120b-UD-Q4_K_XL-00001-of-00002.gguf49.9 GB257490fe05412bfd11dd7f4296b2c9105527a952cd2dac034049ecb33f87a2e5
UD-Q4_K_XL/gpt-oss-safeguard-120b-UD-Q4_K_XL-00002-of-00002.gguf13.1 GB8bf979ac67952541fb31c4a395a5ce1dc10135234b142aba1973b58bdc20baab
UD-Q6_K_XL/gpt-oss-safeguard-120b-UD-Q6_K_XL-00001-of-00002.gguf49.5 GB3a09c2a0c2ab92e136c356a8c451b746c10eed46ba4eb45dd8e5b5e404b4aa64
UD-Q6_K_XL/gpt-oss-safeguard-120b-UD-Q6_K_XL-00002-of-00002.gguf13.8 GBb1114cc9554131c5ed701f0c229b2e1337c572f918c9119015a48ad302109052
UD-Q8_K_XL/gpt-oss-safeguard-120b-UD-Q8_K_XL-00001-of-00002.gguf49.5 GB752a8fac08094d9dc67f98f9e702030e9bd2d6b9ffa2ecfc85bb941c978c4b41
UD-Q8_K_XL/gpt-oss-safeguard-120b-UD-Q8_K_XL-00002-of-00002.gguf14.9 GBecf1b5404bf1cd4009159642b58d8c983e39f663949f455cea2fb21845a9be86
VersionsEach time the pinned upstream commit or file list changed in this repo. Newest first.
Upstream commitDateContents
9a41d614d8 pinned now2026-11-15 05:11 UTC32 files · 945 GB

Use it

$ fw get unsloth/gpt-oss-safeguard-120b-GGUF
# manifest sha256 b0a3f8e22e6c… · 945 GB · 32 files
$ fw verify ./gpt-oss-safeguard-120b-GGUF unsloth/gpt-oss-safeguard-120b-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-120b-GGUF.json --dir ./gpt-oss-safeguard-120b-GGUF $ python3 fw.py verify ./gpt-oss-safeguard-120b-GGUF ./unsloth__gpt-oss-safeguard-120b-GGUF.json
hfThe Hugging Face CLI with one setting. Same repo id.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download unsloth/gpt-oss-safeguard-120b-GGUF --revision 9a41d614d8fe4d54ef6dd6ea8c20d95749e48e7a --local-dir ./gpt-oss-safeguard-120b-GGUF
llama.cppDownload one GGUF variant (Q3_K_S, 62.6 GB), then serve it.
$ HF_ENDPOINT=https://freeweights.allternit.com hf download unsloth/gpt-oss-safeguard-120b-GGUF --include "Q3_K_S/*" --local-dir ./gpt-oss-safeguard-120b-GGUF $ llama-server -m ./gpt-oss-safeguard-120b-GGUF/Q3_K_S/gpt-oss-safeguard-120b-Q3_K_S-00001-of-00002.gguf
OllamaMake an Ollama model from the downloaded file.
$ printf 'FROM ./gpt-oss-safeguard-120b-GGUF/Q3_K_S/gpt-oss-safeguard-120b-Q3_K_S-00001-of-00002.gguf\n' > Modelfile $ ollama create gpt-oss-safeguard-120b-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
e355f169ad310a40fd2feb5f90e9997626d6953f41b9a2593e926da5b64eb3cc
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-120b-GGUFDate: 2026-11-15Commit: 9a41d61Signed: 2DC28CC7B26A283B ✓
Upstream
unsloth/gpt-oss-safeguard-120b-GGUF
Pinned commit
9a41d614d8fe4d54ef6dd6ea8c20d95749e48e7a
Manifest
gpt-oss-safeguard-120b-GGUF.json · .minisig
Manifest sha256
b0a3f8e22e6c145ca875e180d0507511c76a4b22faadfc96e54b855230d156a8
Signature
minisign, Ed25519, key 2DC28CC7B26A283B
Created
2026-11-15 05:11 UTC
Generator
freeweights-manifest/0.1.0
Takedowns
None.

How to verify

$ curl -O https://freeweights.allternit.com/manifests/unsloth/gpt-oss-safeguard-120b-GGUF.json $ curl -O https://freeweights.allternit.com/manifests/unsloth/gpt-oss-safeguard-120b-GGUF.json.minisig $ minisign -Vm gpt-oss-safeguard-120b-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-120b · 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-120b-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-120b-GGUF.json. Provenance. Takedown history: none.
Source
huggingface.co/unsloth/gpt-oss-safeguard-120b-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