nvidia/llama-nemotron-embed-1b-v2 download history

nvidia/llama-nemotron-embed-1b-v2 is a 1.2B-parameter feature extraction model by nvidia. In the last 30 days it was downloaded 350,415 times (84,384 in the last 7 days), and 4,862,698 times in total.

It ranks #999 on the Hub by monthly downloads and #44 among feature extraction models.

It has 72 likes.

5 models build on llama-nemotron-embed-1b-v2: 4 quantized, 1 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 354,708 times in the last 30 days. See the llama-nemotron-embed-1b-v2 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 2026-11-18350,415+4%
October 2026338,481-16%
September 2026403,689-39%
August 2026657,651-18%
July 2026801,465+29%
June 2026622,178-18%
May 2026760,348+7%
April 2026713,195+1048%
March 202662,105+65%
February 202637,563+55%
January 202624,261+134%
December 202510,368-51%

Its busiest 30 days so far ended on 2026-05-07, with 876,231 downloads.

Open nvidia/llama-nemotron-embed-1b-v2 on Hugging Face

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