NVIDIA Nemotron 3.5 Embed 1B
Embedding modelOpen weightsCard summarizedA versatile embedding model developed by NVIDIA for multimodal and multilingual question-answering retrieval
Where to call it
- Self-host (weights)
nvidia/Nemotron-3.5-Embed-1B-BF16 - NVIDIA API catalog (build.nvidia.com)
nvidia/nemotron-3.5-embed-1b
Good for
- Multimodal question-and-answer retrieval over large document corpora
- Embedding page images with text, tables, charts and infographics
- Semantic search and (agentic) RAG pipelines
Overview
3.5 Embed 1B
A versatile embedding model developed by NVIDIA for multimodal and multilingual question-answering retrieval
- Dimensions
- 2048
- Max input
- 32,768 tokens
- Modes
- text embeddings, image embeddings
- Released
- 20 Oct 2026
Nemotron 3.5 Embed 1B is NVIDIA's open-weights multimodal, multilingual embedding model for question-answering retrieval. It embeds document pages as images, text, or image + text, and retrieves them from text queries; pages can contain text, tables, charts and infographics. It was distilled from Nemotron 3.5 Embed 8B on top of the frozen Nemotron 3 Embed 1B text model, so it shares that model's text embedding space. Output is one 2048-d L2-normalized vector per input, with a 32,768-token context. model card: Description, Model Architecture
nvidia/Nemotron-3.5-Embed-1B-BF16- Typical price
- —
- Dimensions
- 2048 (can be truncated from the end, e.g. 1024 or 512; re-normalize after truncating)
- Max input
- 32,768 tokens (text and image tokens combined)
- Languages
- 34 languages evaluated for text retrieval, 18 for image retrieval
- Weights
- Open · OpenMDW License Agreement 1.1
- Released
- 20 Oct 2026
- text embeddings
- image embeddings
- multimodal embeddings (image + text documents)
- visual document retrieval