BREAKING
NVIDIA Nemotron-3-Embed Tops RTEB
0
%
RTEB
0
%
MMTEB Retrieval
0
B
parameters
0
dimensions
0
k
context window
0
languages
Two Smaller Variants Shipped
1B-BF16
72.4% RTEB
●
1.14B parameters
●
2,048-dim embeddings
1B-NVFP4
Blackwell
●
4-bit quantized
●
Up to 2x throughput
Open Weights on Hugging Face
Built for RAG and AI Agents
AI NEWS BLITZ
NVIDIA has launched Nemotron-3-Embed, a new family of open-weight text embedding models.