gpt-oss-safeguard 120B on Apple M2 Max (96 GB)

Can the Apple M2 Max (96 GB) run gpt-oss-safeguard 120B?

Barely: it runs very slowly (over GPU memory limit)

Very slow (over GPU memory limit). At MXFP4 it needs about 73.0 GB of 72.0 GB usable and makes one decision in about 3.1 s.

Best quant: MXFP4
Time per decision: 3.1 s
Decisions per second: 0.3/s
Input assumed: 512 tokens
Returns: Reasoned verdict

Best app to run it on the Apple M2 Max (96 GB)

On macOS

LM Studio

Desktop app · runs on llama.cpp, MLX · use the MLX build

Splits the model between GPU memory and system RAM, which this setup needs.
Point-and-click: search, download and chat in one window.

Open gpt-oss-safeguard 120B in LM Studio

Ollama Splits the model between GPU memory and system RAM, which this setup needs.
llama.cpp Splits the model between GPU memory and system RAM, which this setup needs.

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 58/100 (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: A+ 85+ · A 70+ · B 55+ · C 40+ · D under 40.
Runs Very slowover GPU memory limit: How well it runs on the Apple M2 Max (96 GB): 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 the model fits in the share of unified memory the GPU can use; fewer when it goes past that limit.	10.0 / 25
SpeedTime for one decision against a 100 ms target: reading the input plus any tokens the model writes.	2.7 / 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	58.7 / 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 Apple M2 Max (96 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`MXFP4`	73.0 GB	72.0 GB	3.1 s	Very slowover GPU memory limit	80Great quality (A) · 80 of 100: how capable the model is at MXFP4, whatever it runs on. Match score 58/100 (quality, fit, speed and memory use) sets the ranking.	Original weights (opens in a new tab)
`F16`	240 GB	72.0 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 75/100 (quality, fit, speed and memory use) sets the ranking. NVIDIA RTX PRO 6000 Blackwell MXFP4 · 918 ms · Slow
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 B200 MXFP4 · 643 ms · Slow
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. AMD Instinct MI350X MXFP4 · 663 ms · Slow
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 GB300 Grace Blackwell Ultra Desktop Superchip MXFP4 · 675 ms · Slow
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. AMD Instinct MI325X MXFP4 · 688 ms · Slow
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 H200 141GB SXM MXFP4 · 699 ms · Slow

Quick answers

How much memory does gpt-oss-safeguard 120B need on the M2 Max 96GB?

At MXFP4 it needs about 73.0 GB. The M2 Max 96GB has 72.0 GB usable.

How fast is gpt-oss-safeguard 120B on the M2 Max 96GB?

It makes one decision in about 3.1 s at MXFP4, an estimate from the hardware and the size of the model.

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.