Mac Compute Rentals › Will it fit?
Will Llama-4-Maverick-17B-128E-Instruct fit on a 512GB Mac Studio (M3 Ultra)?
Yes. Llama-4-Maverick-17B-128E-Instruct-6bit (304 GiB) fits in one 512GB M3 Ultra Mac Studio.
meta-llama/Llama-4-Maverick-17B-128E-Instruct: 402B parameters. License: other.
| MLX weights | Size | On 512GB (~469 GiB GPU limit) |
|---|---|---|
| mlx-community/Llama-4-Maverick-17B-128E-Instruct-4bit | 210.4 GiB | Fits, ~258 GiB left for context |
| mlx-community/Llama-4-Maverick-17B-128E-Instruct-6bit Measured on our Studios: 36.4 tok/s generation at 2K, 31.3 tok/s at 16K | 303.9 GiB | Fits, ~165 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-4-Maverick-17B-128E-Instruct-6bit
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