cognitivecomputations
/

DeepSeek-R1-AWQ

Text Generation

4-bit precision

Model card Files Files and versions Community

Resources

View closed (3)

MLA is not supported with moe_wna16 quantization. Disabling MLA.

#7 opened about 5 hours ago by

skips the thinking process

#5 opened 4 days ago by

The inference performance of the DeepSeek-R1-AWQ model is weak compared to the DeepSeek-R1 model

#3 opened 6 days ago by

Deployment framework

#2 opened 19 days ago by