tokenlabsdotrun
/

Llama-3.1-8B-ModelOpt-NVFP4-QAT

nvidia-modeloptimizer

8-bit precision

Model card Files Files and versions

Llama-3.1-8B-ModelOpt-NVFP4-QAT / generation_config.json

Commit History

Upload Llama-3.1-8B quantized with ModelOpt NVFP4-QAT

a56fce3
verified

genai2eliza commited on Jan 20