NVIDIA Releases Nemotron 3.5 Embed/Rerank/Parse Open-Source Retrieval Models
Understand the story
On October 21, 2026, NVIDIA announced via the Hugging Face Blog the addition of three open-source, commercially usable models to its Nemotron Retriever series: Nemotron 3.5 Embed (available in 8B/1B BF16 and a 1B NVFP4 version), Nemotron 3.5 Rerank 8B, and the 631M-parameter Nemotron 3.5 Parse. These models target enterprise Agent scenarios, handling multimodal retrieval (Embed), reranking (Rerank), and document parsing (Parse) respectively. The event is still at the announcement stage, with no follow-up reports yet.
AI overview of reporting · Updated 1 h前
Reporting timeline
Explore different aspects of the story through its reporting.
- Hugging Face BlogSelectedNVIDIA Nemotron 3.5 Embed, Rerank, and Parse: Advancing Agents with World-Class Retrieval Models
NVIDIA has added open-source, commercially usable models to its Nemotron Retriever series: Nemotron 3.5 Embed (8B/1B BF16, 1B NVFP4), Nemotron 3.5 Rerank 8B, and the 631M-parameter Nemotron 3.5 Parse, targeting multimodal retrieval, reranking, and document parsing for enterprise agents.
Story heat trend
Not enough continuous observations to show a trend yet.