The nvidia/llama-nv-embed-reasoning-3b galaxy

6 models are built on nvidia/llama-nv-embed-reasoning-3b: 3 quantized, 2 fine-tuned, 1 adapters and 0 merges. Together they were downloaded 7,700 times in the last 30 days.

Most downloaded direct derivatives

• mradermacher/llama-nv-embed-reasoning-3b-GGUF (quantized), 330 downloads in 30 days
• DataScience-UIBK/OBLIQ-IR-3B-no-distill (finetune), 82 downloads in 30 days
• DataScience-UIBK/OBLIQ-IR-3B (finetune), 76 downloads in 30 days
• DataScience-UIBK/OBLIQ-IR-3B-LoRA (adapter), 29 downloads in 30 days