Mac Compute Rentals › Will it fit?
Will Llama-3.1-405B-Instruct fit on a 512GB Mac Studio (M3 Ultra)?
Yes. Llama-3.1-405B-Instruct-8bit (402 GiB) fits in one 512GB M3 Ultra Mac Studio.
meta-llama/Llama-3.1-405B-Instruct: 406B parameters. License: llama3.1.
| MLX weights | Size | On 512GB (~469 GiB GPU limit) |
|---|---|---|
| mlx-community/Meta-Llama-3.1-405B-4bit | 214.8 GiB | Fits, ~254 GiB left for context |
| mlx-community/Llama-3.1-405B-Instruct-8bit | 401.6 GiB | Fits, ~67 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/Llama-3.1-405B-Instruct-8bit
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