nvidia/NV-Embed-v2 download history

nvidia/NV-Embed-v2 is a 7.9B-parameter feature extraction model by nvidia. In the last 30 days it was downloaded 211,128 times (50,992 in the last 7 days), and 2,573,699 times in total.

It ranks #1,450 on the Hub by monthly downloads and #63 among feature extraction models.

It has 525 likes.

7 models build on NV-Embed-v2: 0 quantized, 6 fine-tuned, 1 adapters and 0 merges. Together with the original they were downloaded 211,320 times in the last 30 days. See the NV-Embed-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 2026-11-18211,128-32%
October 2026310,254+717%
September 202637,965+129%
August 202616,595-16%
July 202619,658-19%
June 202624,254-35%
May 202637,467-8%
April 202640,582-52%
March 202684,842+86%
February 202645,544-19%
January 202655,944+43%
December 202539,140-82%

Its busiest 30 days so far ended on 2025-02-21, with 383,756 downloads.

Open nvidia/NV-Embed-v2 on Hugging Face

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