nvidia/Nemotron-3.5-Rerank-8B-BF16 download history
nvidia/Nemotron-3.5-Rerank-8B-BF16 is an 8.4B-parameter text ranking model by nvidia. In the last 30 days it was downloaded 8,406 times (1,669 in the last 7 days), and 9,627 times in total.
It ranks #9,423 on the Hub by monthly downloads and #51 among text ranking models.
It has 52 likes.
It is a fine-tune of mistralai/Ministral-3-8B-Instruct-2512-BF16.
6 models build on Nemotron-3.5-Rerank-8B-BF16: 5 quantized, 1 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 9,927 times in the last 30 days. See the Nemotron-3.5-Rerank-8B-BF16 galaxy.
Most downloaded derivatives
- netprojects/Nemotron-3.5-Rerank-8B-GGUF (quantized), 955 downloads in 30 days
- netprojects/Nemotron-3.5-Rerank-8B-mlx-4bit (quantized), 136 downloads in 30 days
- netprojects/Nemotron-3.5-Rerank-8B-mlx-8bit (quantized), 131 downloads in 30 days
- OpenGryd/Nemotron-3.5-Rerank-8B-MLX-8bit (finetune), 114 downloads in 30 days
- ElytronSystems/Nemotron-3.5-Rerank-pulsar-k4 (quantized), 105 downloads in 30 days
- HangGlidersRule/Darkstar-Nemotron-3.5-Rerank-8B-Base-ModelOpt-W4A4-NVFP4 (quantized), 80 downloads in 30 days
Downloads by month
Downloads in the 30 days up to the end of each month, and the change from the month before.
| Month | Downloads | Change |
|---|---|---|
| Up to 2026-11-18 | 8,406 | +68% |
Its busiest 30 days so far ended on 2026-11-18, with 8,406 downloads.
Open nvidia/Nemotron-3.5-Rerank-8B-BF16 on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.