Not established from the available sources.
NVIDIA · MODEL RELEASE TRACKER
Nemotron 3.5 Embed 1B BF16
Nemotron 3.5 Embed 1B BF16 is an embedding model in NVIDIA's Nemotron Retriever collection. It is presented as an open, commercially available retrieval model for agent workflows and was evaluated on multimodal and text-only retrieval benchmarks.CURRENT SNAPSHOT3/5 DIMENSIONS WITH DATA
The dimensions that change the decision.
Not established from the available sources.
ModalityBrought as part of models enabling multimodal retrieval (supports combined text and image inputs, per evaluation on ViDoRe v3).
Benchmark evaluationEvaluated in retrieval/agent experiments across ViDoRe v3, BRIGHT, and BrowseComp-Plus to measure agent retrieval quality and total agent inference cost.
AvailabilityDescribed as open and commercially available.
RELEASE TIMELINE
Published, source-backed release events only.
VERIFIABLE FACTS
Every value stays attached to a source and date.
RELEASE · Release / collection inclusionDEVELOPER CLAIM
Named by NVIDIA as a new addition to the Nemotron Retriever collection (Nemotron 3.5 Embed 8B BF16, 1B BF16, 1B NVFP4 were listed together).
CAPABILITIES · Primary functionDEVELOPER CLAIM
Serves as an embedding model used for retrieval to support agent search and evidence collection.
AVAILABILITY · AvailabilityDEVELOPER CLAIM
Described as open and commercially available.
MODALITIES · ModalityDEVELOPER CLAIM
Brought as part of models enabling multimodal retrieval (supports combined text and image inputs, per evaluation on ViDoRe v3).
BENCHMARKS · Benchmark evaluationDEVELOPER CLAIM
Evaluated in retrieval/agent experiments across ViDoRe v3, BRIGHT, and BrowseComp-Plus to measure agent retrieval quality and total agent inference cost.
WHAT CHANGED