NVIDIA Open-Sources Nemotron 3.5 Retriever Suite

NVIDIA released an open, commercially usable Nemotron Retriever suite on Hugging Face, including Embed 8B/1B (with NVFP4 quantization), Rerank 8B, and a 631M multimodal parse model, aimed at saving inference tokens for agents.

2026-10-30 ~ 2026-10-30 · 2 related posts

• NVIDIA releases open Nemotron 3.5 Embed, Rerank and Parse models to cut agent token costs — NVIDIAAI · 2026-10-30
• NVIDIA open-sources Nemotron 3.5 Embed, Rerank and Parse models to cut agent inference token waste — NVIDIAAI · 2026-10-30