Mac Compute Rentals › Will it fit?
Will Qwen3-Coder-480B-A35B-Instruct fit on a 512GB Mac Studio (M3 Ultra)?
Yes. Qwen3-Coder-480B-A35B-Instruct-4bit (252 GiB) fits in one 512GB M3 Ultra Mac Studio.
Qwen/Qwen3-Coder-480B-A35B-Instruct: 480B parameters. License: apache-2.0.
| MLX weights | Size | On 512GB (~469 GiB GPU limit) |
|---|---|---|
| mlx-community/Qwen3-Coder-480B-A35B-Instruct-4bit | 251.5 GiB | Fits, ~217 GiB left for context |
| mlx-community/Qwen3-Coder-480B-A35B-Instruct-8bit | 503.1 GiB | Doesn't fit, 34 GiB over the limit |
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/Qwen3-Coder-480B-A35B-Instruct-4bit
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