parasail-ai
/

Llama-3.1-8B-Instruct-NVFP4A16

8-bit precision

compressed-tensors

Model card Files Files and versions Community

Llama-3.1-8B-Instruct-NVFP4A16

Ctrl+K

Ctrl+K

1 contributor

History: 2 commits

Parasail's picture

Upload FP4 quantized model

166764e verified about 1 month ago