gpt-oss-safeguard 120B on Apple M2 (16 GB)

Can the Apple M2 (16 GB) run gpt-oss-safeguard 120B?

No, it doesn’t fit

No. gpt-oss-safeguard 120B needs about 68.1 GB even at MXFP4; the Apple M2 (16 GB) has 10.7 GB usable.

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 10/100 (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 Won't run: How well it runs on the Apple M2 (16 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.	10.8 / 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.	0.0 / 25
SpeedTime for one decision against a 100 ms target: reading the input plus any tokens the model writes.	0.0 / 15
ClarityHow easy the answer is to use in code: a probability or score earns the most, written feedback before a score the least.	0.0 / 15
Match score	10.8 / 100

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

It doesn’t fit, so only a reduced share of the quality points counts and fit, speed and memory use score zero.

Every quantization on the Apple M2 (16 GB)

Quant	Memory needed	Available	Speed	Runs	Quality	Download
`MXFP4`	68.1 GB	10.7 GB	—	Won't run	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`	235 GB	10.7 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.

Hardware that can run 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

Models that do run on the Apple M2 (16 GB)

80Great quality (A) · 80 of 100: how capable the model is at F16, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking. GLiNER2.5 Decide F16 · 74 ms
86Excellent quality (A+) · 86 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. Jina Reranker v3.5 Q8_0 · 153 ms
80Great quality (A) · 80 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 90/100 (quality, fit, speed and memory use) sets the ranking. FRIDA-Decisions Q8_0 · 106 ms
84Great quality (A) · 84 of 100: how capable the model is at Q8_0, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Jina Reranker v3 Q8_0 · 153 ms
76Great quality (A) · 76 of 100: how capable the model is at F16, whatever it runs on. Match score 89/100 (quality, fit, speed and memory use) sets the ranking. Llama Prompt Guard 2 86M F16 · 84 ms

Quick answers

How much memory does gpt-oss-safeguard 120B need on the M2 16GB?

Even at MXFP4 it needs about 68.1 GB; the M2 16GB has 10.7 GB usable.

What can the M2 16GB run instead?

GLiNER2.5 Decide, Jina Reranker v3.5 and FRIDA-Decisions run best on it; the page lists more, each with its speed.

What hardware can run gpt-oss-safeguard 120B?

NVIDIA RTX PRO 6000 Blackwell 96GB, NVIDIA B200 180GB and AMD Instinct MI350X 288GB run it; the page lists more, each with its speed.

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.