Decision models ·

gpt-oss-safeguard 20B

Task
Safety and policy checks
Returns
Reasoned verdict
Precision tier
76 / 100
Size
22B (3.6B active)
Max input
128K tokens
License
apache-2.0
Released
2025-10

What it decides

Returns
Reasons step by step over a policy you write, then gives a label; reasoning effort is adjustable (low, medium, high).
Checks
Any content against your own policy
Languages
English
Precision
76 / 100 · Policy-following classifier from OpenAI and ROOST; scored low (F1 0.38) on a fixed-taxonomy benchmark that does not supply a policy (arXiv 2605.28830).
Clarity
Reasoned verdict (10 of 15 clarity points) · writes about 160 tokens before the answer, so it is slower but explains itself.
How it runs
Writes a short answer · a small language model, so it runs in the same apps as LLMs.
License
apache-2.0 (Open (Apache, MIT))

Source: model card on Hugging Face (opens in a new tab) · How decision models are rated

How to run it

Quickest · Ollama

One command downloads a ready-to-run version and starts a chat.

Get Ollama at ollama.com/download (opens in a new tab) · model page (opens in a new tab)

ollama run gpt-oss-safeguard:20b

Quantized files · GGUF

Works in LM Studio, llama.cpp, Jan and Ollama. No sign-in needed.

huggingface.co/unsloth/gpt-oss-safeguard-20b-GGUF (opens in a new tab)

ollama run hf.co/unsloth/gpt-oss-safeguard-20b-GGUF

Original weights · Hugging Face

Full-precision files from OpenAI, for fine-tuning, vLLM, Transformers.

huggingface.co/openai/gpt-oss-safeguard-20b (opens in a new tab)

No sign-in needed.

Links checked 3 days ago against Hugging Face, Ollama and GitHub.

Apps that run gpt-oss-safeguard 20B

Our pick for each kind of computer, assuming the model fits in its memory. Pick your own GPU or Mac in the Model Finder for an exact answer.

Mac (Apple silicon)

LM Studio

Runs the MLX build, typically 35–90% faster than GGUF for a model with 3.6B active parameters on Apple silicon.

Also good: MLX LM, Ollama

Windows PC, NVIDIA GPU

Ollama

One command with Ollama’s own build of this model.

Also good: LM Studio, llama.cpp

Windows PC, AMD Radeon

Lemonade

AMD’s own app: llama.cpp tuned for Radeon on Vulkan and ROCm.

Also good: LM Studio, Ollama

Linux, NVIDIA GPU

Ollama

One command with Ollama’s own build of this model.

Also good: LM Studio, llama.cpp

Linux server, 80 GB+ GPUs

vLLM

The full model fits in GPU memory at 8-bit, so it can batch many requests: best for serving a team or an app.

Also good: Ollama, LM Studio

App Type Opens it as Systems Engine Start
LM Studio Desktop app GGUF or MLX macOSWindowsLinux llama.cpp, MLX Open in LM Studio
Ollama CLI + API Ollama library macOSWindowsLinux llama.cpp, MLX 
ollama run gpt-oss-safeguard:20b
llama.cpp CLI + API GGUF macOSWindowsLinux llama.cpp 
llama-server -hf unsloth/gpt-oss-safeguard-20b-GGUF:Q4_K_M
Jan Desktop app GGUF or MLX macOSWindowsLinux llama.cpp, MLX Open in Jan
MLX LM CLI + API MLX macOS MLX 
mlx_lm.chat --model lmstudio-community/gpt-oss-safeguard-20b-MLX-MXFP4
vLLM Server Original weights WSLWindowsLinux vLLM 
vllm serve openai/gpt-oss-safeguard-20b
SGLang Server Original weights WSLWindowsLinux SGLang 
python3 -m sglang.launch_server --model-path openai/gpt-oss-safeguard-20b
Docker Model Runner CLI + API GGUF macOSWindowsLinux llama.cpp, vLLM 
docker model run hf.co/unsloth/gpt-oss-safeguard-20b-GGUF:Q4_K_M
Lemonade Desktop app GGUF macOSWindowsLinux llama.cpp, ONNX Runtime GenAI 
lemonade pull unsloth/gpt-oss-safeguard-20b-GGUF:Q4_K_M
Unsloth Desktop Desktop app GGUF or MLX macOSWindowsLinux llama.cpp, MLX, stable-diffusion.cpp Open in Unsloth Desktop
Atomic Chat Desktop app GGUF or MLX macOSWindowsLinux llama.cpp, MLX-VLM Open in Atomic Chat
LocalAI Server GGUF macOSWSLWindowsLinux llama.cpp, rerankers, Transformers Get LocalAI
Sentence Transformers Library Original weights macOSWindowsLinux PyTorch Get Sentence Transformers

Which apps can open a model depends on the files published for it: GGUF for llama.cpp-based apps, MLX for Apple’s engine, the original weights for vLLM and SGLang. Compare every app.

Memory and speed

Each quantization on an NVIDIA GeForce RTX 4090, for one decision on a 512-token input. The best hardware table below covers other GPUs and Macs.

Format Memory needed Time per decision Decisions per second Quality Download
MXFP4 12.9 GB 905 ms 1.1/s 76Great quality (A) · 76 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 74/100 (quality, fit, speed and memory use) sets the ranking. Original weights (opens in a new tab)
F16 43.7 GB — — 76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. GGUF (opens in a new tab) Original weights (opens in a new tab)

One request at a time. Servers that batch (Text Embeddings Inference, vLLM, Infinity) handle many more decisions per second.

Best hardware for gpt-oss-safeguard 20B

The least expensive GPU in our catalog that runs it without offloading is the AMD Radeon RX 7600 XT (launch price $329) at MXFP4.

Quality Hardware Quant Memory Time per decision Runs
76Great quality (A) · 76 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA B200NVIDIA B200 MXFP4 21.9 GB / 180 GB 130 ms Runs great
76Great quality (A) · 76 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking. AMD Instinct MI350XAMD Instinct MI350X MXFP4 27.3 GB / 288 GB 153 ms Runs well
76Great quality (A) · 76 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 80/100 (quality, fit, speed and memory use) sets the ranking. AMD Instinct MI325XAMD Instinct MI325X MXFP4 25.7 GB / 256 GB 192 ms Runs well
76Great quality (A) · 76 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H200 141GB SXMNVIDIA H200 141GB SXM MXFP4 20.0 GB / 141 GB 206 ms Runs well
76Great quality (A) · 76 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H200 NVLNVIDIA H200 NVL MXFP4 20.0 GB / 141 GB 208 ms Runs well
76Great quality (A) · 76 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking. AMD Instinct MI300XAMD Instinct MI300X MXFP4 22.5 GB / 192 GB 214 ms Runs well
76Great quality (A) · 76 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA GH200 Grace Hopper (96 GB GPU)NVIDIA GH200 Grace Hopper (96 GB GPU) MXFP4 17.7 GB / 96.0 GB 242 ms Runs well
76Great quality (A) · 76 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H100 NVLNVIDIA H100 NVL MXFP4 17.6 GB / 94.0 GB 250 ms Runs well
76Great quality (A) · 76 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H20 MXFP4 17.7 GB / 96.0 GB 281 ms Runs well
76Great quality (A) · 76 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA H100 80GB SXMNVIDIA H100 80GB SXM MXFP4 16.9 GB / 80.0 GB 285 ms Runs well

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.