Skip to content

DeepSeek-R1-0528-5bit

mlx-community/DeepSeek-R1-0528-5bit
5-bit Open on Hugging Face
Parameters
671B
Weights (est.)
≈ 461 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-R1-0528-5bit --prompt "Hello"

Details

Base model
deepseek-ai/DeepSeek-R1-0528 (quantized)
Vendor
DeepSeek
Task
Text generation
Quantisation
5-bit
Licence
mit
Downloads
50 in the last 30 days · 1.9K all time · 3 likes
Published
2025-06-30 · updated 2025-07-01 (1y ago)
Tags
deepseek_v3, custom_code

Other MLX builds of deepseek-ai/DeepSeek-R1-0528

Build Quantisation Weights Mac memory Downloads
DeepSeek-R1-0528-3bit 3-bit ≈ 294 GB 512 GB+ 69
DeepSeek-R1-0528-5bit (this one) 5-bit ≈ 461 GB > 512 GB 50