gpt-oss-safeguard 120B on NVIDIA H200 141GB SXM

Can the NVIDIA H200 141GB SXM run gpt-oss-safeguard 120B?

Yes, it runs well

Runs well. At MXFP4 it needs about 74.3 GB of 141 GB usable and makes one decision in about 290 ms.

Best quant: MXFP4
Time per decision: 290 ms
Decisions per second: 3.4/s
Input assumed: 512 tokens
Returns: Reasoned verdict

Best app to run it on the NVIDIA H200 141GB SXM

On Linux

vLLM

Inference server · runs on 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.

vllm serve openai/gpt-oss-safeguard-120b

Ollama One command with Ollama’s own build of this model.
LM Studio Point-and-click: search, download and chat in one window.

On Windows

Ollama

Command line + local API · runs on llama.cpp (ggml), MLX (Apple silicon, preview)

One command with Ollama’s own build of this model.
Serves an OpenAI-compatible API that other apps and coding tools can use.

ollama run gpt-oss-safeguard:120b

LM Studio Point-and-click: search, download and chat in one window.
llama.cpp Usually the first to support new model architectures.

How we choose: the files published for this model, your operating system and GPU, whether it fits fully in memory, and published speed tests (MLX vs llama.cpp on Apple silicon, vLLM vs llama.cpp vs Ollama on NVIDIA). Details.

Download gpt-oss-safeguard 120B

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 3 days ago against Hugging Face, Ollama and GitHub.

How it’s rated

Quality 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.: How capable the model itself is at MXFP4, from its editorial quality tier scaled by the quantization or precision. It’s the same on any hardware that runs this variant. Scale: S 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Runs well: How well it runs on the NVIDIA H200 141GB SXM: speed, capped by how well it fits in memory. Runs great: 30+ tokens/s (or near the image, video or decision speed target) · Runs well: 10+ tokens/s · Slow: 3+ tokens/s · Very slow: under 3 · Won’t run: doesn’t fit even with offload. A tight fit or RAM offload caps it at Runs well; heavy offload caps it at Slow.

Match score

To order lists, each result also gets a match score out of 100 from four parts. It favors the most capable model that still runs well.

PrecisionEditorial precision tier from the model’s published benchmarks, scaled by the quantization or precision used.	36.0 / 45
Memory fitFull marks when everything sits in GPU memory; fewer when part spills to system RAM.	25.0 / 25
SpeedTime for one decision against a 100 ms target: reading the input plus any tokens the model writes.	8.8 / 15
ClarityHow easy the answer is to use in code: a probability or score earns the most, written feedback before a score the least.	10.0 / 15
Match score	79.8 / 100

The match score orders results; it is not shown as a grade. Quality and Runs are the two ratings in the tables.

Every quantization on the NVIDIA H200 141GB SXM

Quant	Memory needed	Available	Time per decision	Runs	Quality	Download
`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.	Original weights (opens in a new tab)
`F16`	241 GB	141 GB	—	Won't run	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)

Times are for one request with a 512-token input and about 160 tokens written. Batching servers process many requests at once.

Other hardware that runs it

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 B200 MXFP4 · 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 MI350X MXFP4 · 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 MI325X MXFP4 · 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 NVL MXFP4 · 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 MI300X MXFP4 · 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) MXFP4 · 342 ms · Runs well

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.