Decision models ·

gpt-oss-safeguard 120B

Task
Safety and policy checks
Returns
Reasoned verdict
Precision tier
80 / 100
Size
117B (5.1B active)
Max input
128K tokens
License
apache-2.0
Released
2025-10

What it decides

Returns
Reasons over a policy you write, then gives a label.
Checks
Any content against your own policy
Languages
English
Precision
80 / 100 · Larger sibling of the 20B with the same policy-reasoning format.
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:120b

Quantized files · GGUF

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

huggingface.co/unsloth/gpt-oss-safeguard-120b-GGUF (opens in a new tab)

ollama run hf.co/unsloth/gpt-oss-safeguard-120b-GGUF

Original weights · Hugging Face

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

huggingface.co/openai/gpt-oss-safeguard-120b (opens in a new tab)

No sign-in needed.

Links checked 2 days ago against Hugging Face, Ollama and GitHub.

Apps that run gpt-oss-safeguard 120B

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 20–35% faster than GGUF for a model with 5.1B active parameters on Apple silicon.

Also good: Ollama, MLX LM

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:120b
llama.cpp CLI + API GGUF macOSWindowsLinux llama.cpp 
llama-server -hf unsloth/gpt-oss-safeguard-120b-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-120b-MLX-MXFP4
vLLM Server Original weights WSLWindowsLinux vLLM 
vllm serve openai/gpt-oss-safeguard-120b
SGLang Server Original weights WSLWindowsLinux SGLang 
python3 -m sglang.launch_server --model-path openai/gpt-oss-safeguard-120b
Docker Model Runner CLI + API GGUF macOSWindowsLinux llama.cpp, vLLM 
docker model run hf.co/unsloth/gpt-oss-safeguard-120b-GGUF:Q4_K_M
Lemonade Desktop app GGUF macOSWindowsLinux llama.cpp, ONNX Runtime GenAI 
lemonade pull unsloth/gpt-oss-safeguard-120b-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 67.3 GB — — 80Great quality (A) · 80 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 10/100 (quality, fit, speed and memory use) sets the ranking. Original weights (opens in a new tab)
F16 234 GB — — 80Great quality (A) · 80 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. 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 120B

The least expensive GPU in our catalog that runs it without offloading is the NVIDIA RTX PRO 6000 Blackwell (launch price $8,565) at MXFP4.

Quality Hardware Quant Memory Time per decision Runs
80Great quality (A) · 80 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 76.3 GB / 180 GB 182 ms Runs well
80Great quality (A) · 80 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 81.7 GB / 288 GB 215 ms Runs well
80Great quality (A) · 80 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 80.1 GB / 256 GB 270 ms Runs well
80Great quality (A) · 80 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 74.3 GB / 141 GB 290 ms Runs well
80Great quality (A) · 80 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 74.3 GB / 141 GB 293 ms Runs well
80Great quality (A) · 80 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 76.9 GB / 192 GB 302 ms Runs well
80Great quality (A) · 80 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 GH200 Grace Hopper (96 GB GPU)NVIDIA GH200 Grace Hopper (96 GB GPU) MXFP4 72.1 GB / 96.0 GB 342 ms Runs well
80Great quality (A) · 80 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 72.0 GB / 94.0 GB 353 ms Runs well
80Great quality (A) · 80 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 72.1 GB / 96.0 GB 397 ms Runs well
80Great quality (A) · 80 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 76/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell Workstation EditionNVIDIA RTX PRO 6000 Blackwell MXFP4 72.1 GB / 96.0 GB 726 ms Slow

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.