Mac Compute Rentals › Will it fit?
Will DeepSeek-V4-Flash-0731 fit on a 512GB Mac Studio (M3 Ultra)?
Yes. DeepSeek-V4-Flash-8bit (144 GiB) fits in one 512GB M3 Ultra Mac Studio.
deepseek-ai/DeepSeek-V4-Flash-0731: 304B parameters. License: mit.
| MLX weights | Size | On 512GB (~469 GiB GPU limit) |
|---|---|---|
| mlx-community/DeepSeek-V4-Flash-4bit | 141.1 GiB | Fits, ~328 GiB left for context |
| mlx-community/DeepSeek-V4-Flash-8bit | 144.4 GiB | Fits, ~324 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/DeepSeek-V4-Flash-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