Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
nvidia
/
Llama-3.3-70B-Instruct-NVFP4
like
32
Follow
NVIDIA
48.3k
Safetensors
llama
8-bit precision
License:
llama3.3
Model card
Files
Files and versions
xet
Community
6
refs/pr/6
Llama-3.3-70B-Instruct-NVFP4
/
tokenizer.json
Commit History
fix truncation in tokenization.json
cd740c0
root
commited on
Aug 22, 2025
Initial commit
ee4a990
zhiyucheng
commited on
Feb 26, 2025