Will gpt-oss-120b fit on a 512GB Mac Studio (M3 Ultra)?

Yes. gpt-oss-120b-MXFP4-Q8 (59 GiB) fits in one 512GB M3 Ultra Mac Studio.

openai/gpt-oss-120b: 117B parameters. License: apache-2.0.

MLX weights	Size	On 512GB (~469 GiB GPU limit)
mlx-community/gpt-oss-120b-MXFP4-Q8 Measured on our Studios: 87.8 tok/s generation, 1,920 tok/s prefill (2K prompt)	59.0 GiB	Fits, ~410 GiB left for context

Sizes: sum of .safetensors files from the Hugging Face API (Oct 2026). "GPU limit" is iogpu.wired_limit_mb=480000, already set on our Studios. Newer architectures may need a recent mlx-lm or llama.cpp; check before you book around one model.

Run it

uv venv ~/mlx && uv pip install --python ~/mlx/bin/python -U mlx-lm
~/mlx/bin/mlx_lm.chat --model mlx-community/gpt-oss-120b-MXFP4-Q8

Try it on a whole 512GB M3 Ultra Mac Studio

3 days $299 · 7 days $489 · 14 days $779. Bare metal, one renter per machine, mlx-lm and llama.cpp ready.

Check availability & book