Not established from the available sources.
NVIDIA · MODEL RELEASE TRACKER
Nemotron 3.5 Embed 8B BF16
Nemotron 3.5 Embed 8B BF16 is an embedding model in NVIDIA's Nemotron 3.5 retriever collection, announced as a new open, commercially available retrieval model. It is intended for embedding-based retrieval, 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.
ModalityPresented as bringing multimodal retrieval capabilities; evaluated on a dataset (ViDoRe v3) that uses combined text and image inputs, alongside text-only datasets.
Benchmark / EvaluationEvaluated (together with Nemotron 3.5 Rerank) across ViDoRe v3, BRIGHT, and BrowseComp-Plus to measure retrieval impact on agent performance and inference cost.
AvailabilityDescribed as open-weight and commercially available.
RELEASE TIMELINE
Published, source-backed release events only.
VERIFIABLE FACTS
Every value stays attached to a source and date.
RELEASE · ReleaseDEVELOPER CLAIM
Announced as part of an expansion of the Nemotron Retriever collection of new open, commercially available models (listed among the new models in the announcement).
CAPABILITIES · CapabilityDEVELOPER CLAIM
Described as an embedding model for retrieval (embedding task).
MODALITIES · ModalityDEVELOPER CLAIM
Presented as bringing multimodal retrieval capabilities; evaluated on a dataset (ViDoRe v3) that uses combined text and image inputs, alongside text-only datasets.
AVAILABILITY · AvailabilityDEVELOPER CLAIM
Described as open-weight and commercially available.
BENCHMARKS · Benchmark / EvaluationDEVELOPER CLAIM
Evaluated (together with Nemotron 3.5 Rerank) across ViDoRe v3, BRIGHT, and BrowseComp-Plus to measure retrieval impact on agent performance and inference cost.
WHAT CHANGED