Skip to content

DeepSeek-R1-0528-8bit

mlx-community/DeepSeek-R1-0528-8bit
8-bit Open on Hugging Face
Parameters
671B
Weights (est.)
≈ 713 GB
Mac memory (est.)
> 512 GB

Size is estimated from the parameter count and quantisation. Memory allows a fifth extra for context plus 2 GB for the system; long contexts need more.

Run it

With mlx-lm on an Apple silicon Mac:

pip install mlx-lmmlx_lm.generate --model mlx-community/DeepSeek-R1-0528-8bit --prompt "Hello"

Details

Base model
—
Vendor
—
Task
Text generation
Quantisation
8-bit
Licence
—
Downloads
40 in the last 30 days · 1.5K all time · 0 likes
Published
2025-08-02 · updated 2025-08-03 (1y ago)
Tags
deepseek_v3, custom_code