Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
tbhot3ww
/
Llama-3.2-3B-Instruct-NVFP4
like
0
Safetensors
llama
nvfp4
quantized
vllm
hopper
dgx
8-bit precision
modelopt
License:
llama3.2
Model card
Files
Files and versions
xet
Community
main
Llama-3.2-3B-Instruct-NVFP4
Commit History
Create README.md
f22afb2
verified
tbhot3ww
commited on
22 days ago
NVFP4 export (modelopt_fp4) for vLLM
7f032c3
verified
tbhot3ww
commited on
22 days ago
initial commit
f7f7d44
verified
tbhot3ww
commited on
22 days ago