mlx-community
/

DeepSeek-R1-4bit

4-bit precision

Model card Files Files and versions

Resources

View closed (0)

Unexpected Chinese Output from mlx-community/deepseek-r1-4bit in LM Studio

#4 opened about 2 months ago by

can use vllm

#3 opened 6 months ago by

Upload configuration_deepseek.py

#2 opened 7 months ago by

I am unable to load this model.

#1 opened 7 months ago by