nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 download history

nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 is a 123.6B-parameter text generation model by nvidia. In the last 30 days it was downloaded 881,304 times (148,691 in the last 7 days), and 7,889,406 times in total.

It ranks #464 on the Hub by monthly downloads and #88 among text generation models.

It has 440 likes, 1 of them in the last week.

258 models build on NVIDIA-Nemotron-3-Super-120B-A12B-BF16: 76 quantized, 17 fine-tuned, 165 adapters and 0 merges. Together with the original they were downloaded 979,712 times in the last 30 days. See the NVIDIA-Nemotron-3-Super-120B-A12B-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 2026-11-18881,304-26%
October 20261,191,392-1%
September 20261,203,035+18%
August 20261,022,774+25%
July 2026816,522-33%
June 20261,216,655+56%
May 2026779,875+8%
April 2026721,545+277%

Its busiest 30 days so far ended on 2026-09-16, with 1,309,317 downloads.

Open nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 on Hugging Face

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