nvidia/Llama-3.1-Nemotron-70B-Instruct-HF download history

nvidia/Llama-3.1-Nemotron-70B-Instruct-HF is a 70.6B-parameter text generation model by nvidia. In the last 30 days it was downloaded 13,850 times (3,508 in the last 7 days), and 1,944,638 times in total.

It ranks #7,165 on the Hub by monthly downloads and #1,598 among text generation models.

It has 2,071 likes, 1 of them in the last week.

It is a fine-tune of meta-llama/Llama-3.1-70B-Instruct.

1,140 models build on Llama-3.1-Nemotron-70B-Instruct-HF: 695 quantized, 38 fine-tuned, 9 adapters and 398 merges. Together with the original they were downloaded 141,570 times in the last 30 days. See the Llama-3.1-Nemotron-70B-Instruct-HF galaxy.

Most downloaded derivatives

Downloads by month

Downloads in the 30 days up to the end of each month, and the change from the month before.

MonthDownloadsChange
Up to 2026-11-1813,850+2%
October 202613,539-45%
September 202624,498+139%
August 202610,229-74%
July 202639,553+149%
June 202615,880+45%
May 202610,948-1%
April 202611,081-1%
March 202611,240-38%
February 202618,053+334%
January 20264,163-18%
December 20255,055-49%

Its busiest 30 days so far ended on 2025-01-17, with 390,382 downloads.

Open nvidia/Llama-3.1-Nemotron-70B-Instruct-HF on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.