nvidia
/

DeepSeek-R1-FP4

Text Generation

Model card Files Files and versions Community

Resources

View closed (4)

FP4 in attention proj

#9 opened 8 days ago by

can this model run on Hopper GPU

#8 opened 9 days ago by

Can this model work with vLLM?

#7 opened 11 days ago by

Request for Detailed Benchmarking Setup with TensorRT-LLM on B200

#6 opened 12 days ago by

Benchmark results compared to orig fp8 / int4 quants etc?

#1 opened 18 days ago by