NVIDIA's Nemotron-3-Embed-8B-BF16 is an 8 billion parameter embedding model optimized for sentence similarity and semantic feature extraction. It is compatible with the sentence-transformers library and can be used for RAG pipelines, semantic search, and clustering. The model is available in BF16 precision on Hugging Face.
In the Foundation models & chat space, Nemotron 3 Embed 8B takes a focused approach. It focuses on generating high-quality text embeddings for semantic search, retrieval, and similarity applications. It is built as an open-source project for developers. Nemotron 3 Embed 8B is open source under the Apache-2.0 license. It runs on the web, the command line, and embeddable surfaces, and it can be self-hosted.
NVIDIA builds and maintains Nemotron 3 Embed 8B, and the product first shipped in 2023. Development happens publicly on GitHub with 87.2k stars and 3k commits in the last 90 days. Key capabilities include Sentence Embeddings, Feature Extraction, and Sentence Transformers.
Latest indexed changes and source events
nvidia/Nemotron-3-Embed-8B-BF16 verified by the PulseGate indexer
