Skip to content
Weights Not Walls
Menu

openai

gpt-oss-safeguard-20b

Reviewed
Size
20.9B parametersfrom the GGUF metadata of a conversion, because this repo's own weights are packed: unsloth/gpt-oss-safeguard-20b-GGUF
Licence
unknown, Apache License 2.0Our reading, check the licence: You can use, change and redistribute the model, including commercially. Keep the licence and any notices, and say which files you changed; you do not have to publish your changes. It includes a patent licence that ends for anyone who sues over patents in the work.
On the Hub since
18 Sep 2025the date the repo was created
Context length
128k tokensfrom the model's config
Fine-tune
of openai/gpt-oss-20bGptOssForCausalLM
On Hugging Face
openai/gpt-oss-safeguard-20b32k downloads in the last 30 days, 294 likes

Scores

No independent scores for this model in Epoch AI's data. A score is only shown here when Epoch's name for a model matches this repo with certainty; an uncertain match is left out rather than guessed.

Claimed by the maker Claimed

The model card has no claimed scores in a machine-readable form (the card's model-index), so none are shown. The maker may give scores in the card text: read the card.

Other views, which we link to and do not copy: look this model up on Artificial Analysis and the Arena leaderboard.

Run it yourself

file sizes read from the Hub 19 Nov 2026

Memory needed = weights + context cache + 0.50 GB for the runtime. Context cache at 8k tokens: 0.19 GB, worked out from the model's config (openai/gpt-oss-safeguard-20b), at 16-bit precision. Choose a machine above to see a verdict for each format. Method

GGUF for llama.cpp, Ollama, LM Studio and others

unsloth/gpt-oss-safeguard-20b-GGUF (converted by unsloth), 4.5k downloads. Sizes are the real files on the Hub, all parts added up.

FormatSizeMemory neededGet it
Q3_K_S10.7 GBfile size11.4 GB10.7 + 0.19 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/gpt-oss-safeguard-20b-GGUF:Q3_K_S
Ollama
ollama run hf.co/unsloth/gpt-oss-safeguard-20b-GGUF:Q3_K_S
Download
hf download unsloth/gpt-oss-safeguard-20b-GGUF --include "gpt-oss-safeguard-20b-Q3_K_S.gguf" --local-dir gpt-oss-safeguard-20b-GGUF
Q4_010.7 GBfile size11.4 GB10.7 + 0.19 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/gpt-oss-safeguard-20b-GGUF:Q4_0
Ollama
ollama run hf.co/unsloth/gpt-oss-safeguard-20b-GGUF:Q4_0
Download
hf download unsloth/gpt-oss-safeguard-20b-GGUF --include "gpt-oss-safeguard-20b-Q4_0.gguf" --local-dir gpt-oss-safeguard-20b-GGUF
Q3_K_M10.7 GBfile size11.4 GB10.7 + 0.19 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/gpt-oss-safeguard-20b-GGUF:Q3_K_M
Ollama
ollama run hf.co/unsloth/gpt-oss-safeguard-20b-GGUF:Q3_K_M
Download
hf download unsloth/gpt-oss-safeguard-20b-GGUF --include "gpt-oss-safeguard-20b-Q3_K_M.gguf" --local-dir gpt-oss-safeguard-20b-GGUF
Q4_110.8 GBfile size11.5 GB10.8 + 0.19 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/gpt-oss-safeguard-20b-GGUF:Q4_1
Ollama
ollama run hf.co/unsloth/gpt-oss-safeguard-20b-GGUF:Q4_1
Download
hf download unsloth/gpt-oss-safeguard-20b-GGUF --include "gpt-oss-safeguard-20b-Q4_1.gguf" --local-dir gpt-oss-safeguard-20b-GGUF
Q4_K_S10.8 GBfile size11.5 GB10.8 + 0.19 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/gpt-oss-safeguard-20b-GGUF:Q4_K_S
Ollama
ollama run hf.co/unsloth/gpt-oss-safeguard-20b-GGUF:Q4_K_S
Download
hf download unsloth/gpt-oss-safeguard-20b-GGUF --include "gpt-oss-safeguard-20b-Q4_K_S.gguf" --local-dir gpt-oss-safeguard-20b-GGUF
Q4_K_M10.8 GBfile size11.5 GB10.8 + 0.19 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/gpt-oss-safeguard-20b-GGUF:Q4_K_M
Ollama
ollama run hf.co/unsloth/gpt-oss-safeguard-20b-GGUF:Q4_K_M
Download
hf download unsloth/gpt-oss-safeguard-20b-GGUF --include "gpt-oss-safeguard-20b-Q4_K_M.gguf" --local-dir gpt-oss-safeguard-20b-GGUF
Q5_K_S10.9 GBfile size11.6 GB10.9 + 0.19 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/gpt-oss-safeguard-20b-GGUF:Q5_K_S
Ollama
ollama run hf.co/unsloth/gpt-oss-safeguard-20b-GGUF:Q5_K_S
Download
hf download unsloth/gpt-oss-safeguard-20b-GGUF --include "gpt-oss-safeguard-20b-Q5_K_S.gguf" --local-dir gpt-oss-safeguard-20b-GGUF
Q5_K_M10.9 GBfile size11.6 GB10.9 + 0.19 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/gpt-oss-safeguard-20b-GGUF:Q5_K_M
Ollama
ollama run hf.co/unsloth/gpt-oss-safeguard-20b-GGUF:Q5_K_M
Download
hf download unsloth/gpt-oss-safeguard-20b-GGUF --include "gpt-oss-safeguard-20b-Q5_K_M.gguf" --local-dir gpt-oss-safeguard-20b-GGUF
UD-Q4_K_XL11.1 GBfile size11.7 GB11.1 + 0.19 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/gpt-oss-safeguard-20b-GGUF:UD-Q4_K_XL
Ollama
ollama run hf.co/unsloth/gpt-oss-safeguard-20b-GGUF:UD-Q4_K_XL
Download
hf download unsloth/gpt-oss-safeguard-20b-GGUF --include "gpt-oss-safeguard-20b-UD-Q4_K_XL.gguf" --local-dir gpt-oss-safeguard-20b-GGUF
Q6_K11.2 GBfile size11.9 GB11.2 + 0.19 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/gpt-oss-safeguard-20b-GGUF:Q6_K
Ollama
ollama run hf.co/unsloth/gpt-oss-safeguard-20b-GGUF:Q6_K
Download
hf download unsloth/gpt-oss-safeguard-20b-GGUF --include "gpt-oss-safeguard-20b-Q6_K.gguf" --local-dir gpt-oss-safeguard-20b-GGUF
UD-Q6_K_XL11.2 GBfile size11.9 GB11.2 + 0.19 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/gpt-oss-safeguard-20b-GGUF:UD-Q6_K_XL
Ollama
ollama run hf.co/unsloth/gpt-oss-safeguard-20b-GGUF:UD-Q6_K_XL
Download
hf download unsloth/gpt-oss-safeguard-20b-GGUF --include "gpt-oss-safeguard-20b-UD-Q6_K_XL.gguf" --local-dir gpt-oss-safeguard-20b-GGUF
Q8_011.3 GBfile size12.0 GB11.3 + 0.19 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/gpt-oss-safeguard-20b-GGUF:Q8_0
Ollama
ollama run hf.co/unsloth/gpt-oss-safeguard-20b-GGUF:Q8_0
Download
hf download unsloth/gpt-oss-safeguard-20b-GGUF --include "gpt-oss-safeguard-20b-Q8_0.gguf" --local-dir gpt-oss-safeguard-20b-GGUF
UD-Q8_K_XL12.3 GBfile size13.0 GB12.3 + 0.19 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/gpt-oss-safeguard-20b-GGUF:UD-Q8_K_XL
Ollama
ollama run hf.co/unsloth/gpt-oss-safeguard-20b-GGUF:UD-Q8_K_XL
Download
hf download unsloth/gpt-oss-safeguard-20b-GGUF --include "gpt-oss-safeguard-20b-UD-Q8_K_XL.gguf" --local-dir gpt-oss-safeguard-20b-GGUF
F1612.8 GBfile size13.5 GB12.8 + 0.19 + 0.50
Commands
llama.cpp
llama-server -hf unsloth/gpt-oss-safeguard-20b-GGUF:F16
Ollama
ollama run hf.co/unsloth/gpt-oss-safeguard-20b-GGUF:F16
Download
hf download unsloth/gpt-oss-safeguard-20b-GGUF --include "gpt-oss-safeguard-20b-F16.gguf" --local-dir gpt-oss-safeguard-20b-GGUF

MLX for Apple silicon

FormatSizeMemory neededRepo
MLXSiddhJagani/gpt-oss-safeguard-20b-mlx-Q210.0 GBfile size10.7 GB10.0 + 0.19 + 0.50Download page
MLX mxfp4lmstudio-community/gpt-oss-safeguard-20b-MLX-MXFP410.4 GBfile size11.0 GB10.4 + 0.19 + 0.50Download page

Original weights

The maker's own weights are packed into integer tensors, so the safetensors header gives no size we can trust; the repo lists the real file sizes.

hf download openai/gpt-oss-safeguard-20b --local-dir gpt-oss-safeguard-20b
Other conversions (2; sizes not read)

The Hub tags 14 quantised repos as conversions of this model; we read the most downloaded and show the maker's own first.

Run it by API

Hugging Face Inference Providers, fetched 19 Nov 2026, 13:58 UTC

1 provider serves this model through the Hugging Face router. Prices are US dollars per million tokens. Precision is what the provider reports; a lower precision than the original weights can change answers. Live first, then cheapest output.

ProviderInOutContextPrecisionTokens/sFirst tokenUptime 24hToolsJSON
groq??128knot given7520.3 s?yesyes

Through the router, with a Hugging Face token (the router bills your Hugging Face account). Change the name after the colon to pick another provider.

curl https://router.huggingface.co/v1/chat/completions \ -H "Authorization: Bearer $HF_TOKEN" -H "Content-Type: application/json" \ -d '{"model": "openai/gpt-oss-safeguard-20b:groq", "messages": [{"role": "user", "content": "Hello"}]}'

Not built yet: one key for every open model, with BlockRun, and our own tested-quality score per provider. Until then, precision and measured speed are the best guide to a provider here.

Planned for this page Not built yet

Try it in private chat
A link to Solana AI's confidential chat for the models it serves. This model is not listed as served there.
Fine-tune it
Fine-tuning a few base models from this page and publishing the result here.
Creators and earnings
Pages for people who publish fine-tunes and adapters of this model, and what they earn.
Fund and bounties
Bounties for new open models, paid from a public fund. How the fund will work.
Contribute compute
How to give compute to open model work, with Akash.

Model data from the Hugging Face Hub 19 Nov 2026, 13:43 UTC. The repo. Found a mistake on this page? Tell us.