nvidia/llama-embed-nemotron-8b download history
nvidia/llama-embed-nemotron-8b is a 7.5B-parameter feature extraction model by nvidia. In the last 30 days it was downloaded 30,771 times (9,006 in the last 7 days), and 1,419,580 times in total.
It ranks #4,760 on the Hub by monthly downloads and #175 among feature extraction models.
It has 172 likes, 1 of them in the last week.
6 models build on llama-embed-nemotron-8b: 1 quantized, 5 fine-tuned, 0 adapters and 0 merges. Together with the original they were downloaded 31,679 times in the last 30 days. See the llama-embed-nemotron-8b galaxy.
Most downloaded derivatives
- mradermacher/llama-embed-nemotron-8b-GGUF (quantized), 754 downloads in 30 days
- ncorder/llama-embed-nemotron-8b-mlx-4bit (finetune), 48 downloads in 30 days
- ncorder/llama-embed-nemotron-8b-mlx-8bit (finetune), 30 downloads in 30 days
- ncorder/llama-embed-nemotron-8b-mlx-2bit (finetune), 29 downloads in 30 days
- ncorder/llama-embed-nemotron-8b-mlx-fp16 (finetune), 27 downloads in 30 days
- enzoescipy/llama-embed-nemotron-8b-model2vec-pca3 (finetune), 20 downloads in 30 days