RunsOnMy ModelsGPUs & MacsBy VRAMBest GPUCan I run…?OllamaStart hereAPI pricesVRAM calculatorNew

Can gpt-oss Safeguard 120B run on the Mac M4 Max 128GB?

Yes. At 8K context the best fit is Q8_0, using about 60.1 GB of the 96.0 GB usable on the Mac M4 Max 128GB. Estimated speed ceiling: ~175 tokens/sec.

Memory by quant and context

Quant4K ctx8K ctx32K ctx128K ctxMax tok/s (est., 8K)
2-bit (Q2_K) •59.2 GB Fits59.3 GB Fits60.2 GB Fits63.6 GB Fits177
3-bit (Q3_K_M) •59.3 GB Fits59.4 GB Fits60.2 GB Fits63.6 GB Fits177
4-bit (Q4_K_M) •59.4 GB Fits59.5 GB Fits60.4 GB Fits63.7 GB Fits177
5-bit (Q5_K_M) •59.5 GB Fits59.6 GB Fits60.5 GB Fits63.9 GB Fits176
6-bit (Q6_K) •59.9 GB Fits60.0 GB Fits60.9 GB Fits64.2 GB Fits175
8-bit (Q8_0) •60.0 GB Fits60.1 GB Fits60.9 GB Fits64.3 GB Fits175
16-bit (F16/BF16)219 GB No219 GB No220 GB No223 GB No—

• real GGUF file size from unsloth/gpt-oss-safeguard-120b-GGUF. Speed is a bandwidth ceiling (546 GB/s), not a benchmark. Methodology.

What fits instead

"Runs" and "fits" mean the whole model in GPU memory at 8K context (4-bit or better for the model pick). Prices are US launch MSRPs, not today's street prices. "Popular" means the 60 most-downloaded models we track.

More

gpt-oss Safeguard 120B on every GPU and Mac · Every model that runs on the Mac M4 Max 128GB · Apple Silicon guide · Try other settings in the calculator

Guides: Best GPU for local LLMs by budget · Can I run gpt-oss, Llama 70B or Qwen3? · Mac vs PC for local LLMs

Data: Hugging Face Hub (openai/gpt-oss-safeguard-120b), Apple specs. Model data last checked 2026-11-18; refreshed hourly.