nvidia/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct download history

nvidia/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct is an 8.0B-parameter text generation model by nvidia. In the last 30 days it was downloaded 3,178 times (1,045 in the last 7 days), and 42,935 times in total.

It ranks #15,927 on the Hub by monthly downloads and #4,006 among text generation models.

It has 64 likes.

98 models build on Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct: 74 quantized, 16 fine-tuned, 0 adapters and 8 merges. Together with the original they were downloaded 28,492 times in the last 30 days. See the Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct 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 2026-11-183,178+61%
October 20261,969-23%
September 20262,551+538%
August 2026400-41%
July 2026674+29%
June 2026522-46%
May 2026964-79%
April 20264,667+155%
March 20261,830+42%
February 20261,286-54%
January 20262,806+317%
December 2025673+99%

Its busiest 30 days so far ended on 2025-09-24, with 7,238 downloads.

Open nvidia/Llama-3.1-Nemotron-8B-UltraLong-1M-Instruct on Hugging Face

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