nvidia/Nemotron-3-Embed-1B-BF16 download history
nvidia/Nemotron-3-Embed-1B-BF16 is a 1.1B-parameter sentence similarity model by nvidia. In the last 30 days it was downloaded 361,901 times (66,056 in the last 7 days), and 1,287,991 times in total.
It ranks #998 on the Hub by monthly downloads and #64 among sentence similarity models.
It has 159 likes, 5 of them in the last week.
It is a fine-tune of mistralai/Ministral-3-3B-Instruct-2512.
29 models build on Nemotron-3-Embed-1B-BF16: 21 quantized, 7 fine-tuned, 1 adapters and 0 merges. Together with the original they were downloaded 532,253 times in the last 30 days. See the Nemotron-3-Embed-1B-BF16 galaxy.
Most downloaded derivatives
- zenmagnets/Nemotron-3-Embed-1B-Q4_K_M-GGUF (quantized), 100.6K downloads in 30 days
- groxaxo/Nemotron-3-Embed-1B-AWQ-W4A16 (quantized), 49.7K downloads in 30 days
- nvidia/Nemotron-3-Embed-1B-NVFP4 (quantized), 16K downloads in 30 days
- nanoandrew4/Nemotron-3-Embed-1B-GGUF (quantized), 1.2K downloads in 30 days
- NeoRoth/nemotron-3-embed-1b-gguf (quantized), 532 downloads in 30 days
- mlx-community/Nemotron-3-Embed-1B-BF16-8bit (quantized), 362 downloads in 30 days
- mlx-community/Nemotron-3-Embed-1B-BF16-4bit (quantized), 265 downloads in 30 days
- KIEFERSA/Sophea-Nemo-Embedding (finetune), 257 downloads in 30 days
- mlx-community/Nemotron-3-Embed-1B-BF16 (finetune), 242 downloads in 30 days
- malteos/most-embed-de (finetune), 201 downloads in 30 days
- litert-community/Nemotron-3-Embed-1B (quantized), 200 downloads in 30 days
- groxaxo/Nemotron-3-Embed-1B-oQ6-MLX (quantized), 140 downloads in 30 days