nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16 download history

nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16 is a 4.0B-parameter text generation model by nvidia. In the last 30 days it was downloaded 1,804,619 times (92,645 in the last 7 days), and 10,389,279 times in total.

It ranks #217 on the Hub by monthly downloads and #32 among text generation models.

It has 144 likes, 3 of them in the last week.

It is a fine-tune of nvidia/NVIDIA-Nemotron-Nano-9B-v2.

121 models build on NVIDIA-Nemotron-3-Nano-4B-BF16: 61 quantized, 36 fine-tuned, 22 adapters and 2 merges. Together with the original they were downloaded 1,918,341 times in the last 30 days. See the NVIDIA-Nemotron-3-Nano-4B-BF16 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 2026-11-181,804,619-4%
October 20261,886,930-61%
September 20264,860,845+934%
August 2026469,908-35%
July 2026724,255-62%
June 20261,929,605+1352%
May 2026132,886+13%
April 2026117,803+158%

Its busiest 30 days so far ended on 2026-09-29, with 4,871,604 downloads.

Open nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16 on Hugging Face

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