view article Article One Adapter, Both Modalities: Field Notes from Building and Serving a Multimodal Reranker lightonai • 5 days ago • 16
Nemotron 3 Embed Collection Open embedding models for enterprise RAG, agentic retrieval, code search, and agent memory. • 3 items • Updated 5 days ago • 26
Inkling Collection Inkling is a versatile, customizable model that reasons over text, images, audio, with variable and efficient thinking effort. • 2 items • Updated 6 days ago • 33
nvidia/Nemotron-3-Embed-1B-NVFP4 Sentence Similarity • 0.8B • Updated about 22 hours ago • 7.41k • 59
NVFP4 Collection Dynamic Unsloth NVFP4 Quants. Faster and more accurate. • 10 items • Updated 3 days ago • 46
view article Article SLMLogitsClassifier: How SLMs can be adapted to deliver efficient, robust and instruction-aligned classification in a single forward pass UlrickBL • Dec 7, 2025 • 2
llm-semantic-router/mmbert-embed-32k-2d-matryoshka Sentence Similarity • 0.3B • Updated Mar 6 • 8.37k • • 18