nvidia/Llama-4-Scout-17B-16E-Instruct-FP8 download history

nvidia/Llama-4-Scout-17B-16E-Instruct-FP8 is a 108.6B-parameter model model by nvidia. In the last 30 days it was downloaded 18,591 times (3,717 in the last 7 days), and 2,369,561 times in total.

It ranks #5,979 on the Hub by monthly downloads.

It has 17 likes.

It is a quantization of meta-llama/Llama-4-Scout-17B-16E-Instruct.

Open nvidia/Llama-4-Scout-17B-16E-Instruct-FP8 on Hugging Face