bartowski
/

DeepSeek-R1-GGUF

Text Generation

Inference Endpoints

Model card Files Files and versions Community

Resources

View closed (0)

Tested Q6, uses 567Gb Ram

#2 opened 3 days ago by

Using -ctk q4_0 -ctv q4_0 with llama.cpp server throws flash_attn error

#1 opened 4 days ago by